A Digital Liquid State Machine With Biologically Inspired Learning and Its Application to Speech Recognition

Resistive memory-based zero-shot liquid state machine for multimodal event data learning

The human brain is a complex spiking neural network (SNN) capable of learning multimodal signals in a zero-shot manner by generalizing existing knowledge. Remarkably, it maintains minimal power consumption through event-based signal propagation. However, replicating the human brain in neuromorphic hardware presents both hardware and software challenges. Hardware limitations, such as the slowdown of Moore's law and Von Neumann bottleneck, hinder the efficiency of digital computers. In addition, SNNs are characterized by their software training complexities. Here, to this end, we propose a hardware-software co-design on a 40 nm 256 kB in-memory computing macro that physically integrates a fixed and random liquid state machine SNN encoder with trainable artificial neural network projections. We showcase the zero-shot learning of multimodal events on the N-MNIST and N-TIDIGITS datasets, including visual and audio data association, as well as neural and visual data alignment for brain-machine interfaces. Our co-design achieves classification accuracy comparable to fully optimized software models, resulting in a 152.83- and 393.07-fold reduction in training costs compared with state-of-the-art spiking recurrent neural network-based contrastive learning and prototypical networks, and a 23.34- and 160-fold improvement in energy efficiency compared with cutting-edge digital hardware, respectively. These proof-of-principle prototypes demonstrate zero-shot multimodal events learning capability for emerging efficient and compact neuromorphic hardware.

Event-Driven Spiking Learning Algorithm Using Aggregated Labels

Traditional spiking learning algorithm aims to train neurons to spike at a specific time or on a particular frequency, which requires precise time and frequency labels in the training process. While in reality, usually only aggregated labels of sequential patterns are provided. The aggregate-label (AL) learning is proposed to discover these predictive features in distracting background streams only by aggregated spikes. It has achieved much success recently, but it is still computationally intensive and has limited use in deep networks. To address these issues, we propose an event-driven spiking aggregate learning algorithm (SALA) in this article. Specifically, to reduce the computational complexity, we improve the conventional spike-threshold-surface (STS) calculation in AL learning by analytical calculating voltage peak values in spiking neurons. Then we derive the algorithm to multilayers by event-driven strategy using aggregated spikes. We conduct comprehensive experiments on various tasks including temporal clue recognition, segmented and continuous speech recognition, and neuromorphic image classification. The experimental results demonstrate that the new STS method improves the efficiency of AL learning significantly, and the proposed algorithm outperforms the conventional spiking algorithm in various temporal clue recognition tasks.

Snn and sound: a comprehensive review of spiking neural networks in sound

The rapid advancement of AI and machine learning has significantly enhanced sound and acoustic recognition technologies, moving beyond traditional models to more sophisticated neural network-based methods. Among these, Spiking Neural Networks (SNNs) are particularly noteworthy. SNNs mimic biological neurons and operate on principles similar to the human brain, using analog computing mechanisms. This capability allows for efficient sound processing with low power consumption and minimal latency, ideal for real-time applications in embedded systems. This paper reviews recent developments in SNNs for sound recognition, underscoring their potential to overcome the limitations of digital computing and suggesting directions for future research. The unique attributes of SNNs could lead to breakthroughs in mimicking human auditory processing more closely.

Attention-Based Deep Spiking Neural Networks for Temporal Credit Assignment Problems

The temporal credit assignment (TCA) problem, which aims to detect predictive features hidden in distracting background streams, remains a core challenge in biological and machine learning. Aggregate-label (AL) learning is proposed by researchers to resolve this problem by matching spikes with delayed feedback. However, the existing AL learning algorithms only consider the information of a single timestep, which is inconsistent with the real situation. Meanwhile, there is no quantitative evaluation method for TCA problems. To address these limitations, we propose a novel attention-based TCA (ATCA) algorithm and a minimum editing distance (MED)-based quantitative evaluation method. Specifically, we define a loss function based on the attention mechanism to deal with the information contained within the spike clusters and use MED to evaluate the similarity between the spike train and the target clue flow. Experimental results on musical instrument recognition (MedleyDB), speech recognition (TIDIGITS), and gesture recognition (DVS128-Gesture) show that the ATCA algorithm can reach the state-of-the-art (SOTA) level compared with other AL learning algorithms.

Composing recurrent spiking neural networks using locally-recurrent motifs and risk-mitigating architectural optimization

In neural circuits, recurrent connectivity plays a crucial role in network function and stability. However, existing recurrent spiking neural networks (RSNNs) are often constructed by random connections without optimization. While RSNNs can produce rich dynamics that are critical for memory formation and learning, systemic architectural optimization of RSNNs is still an open challenge. We aim to enable systematic design of large RSNNs via a new scalable RSNN architecture and automated architectural optimization. We compose RSNNs based on a layer architecture called Sparsely-Connected Recurrent Motif Layer (SC-ML) that consists of multiple small recurrent motifs wired together by sparse lateral connections. The small size of the motifs and sparse inter-motif connectivity leads to an RSNN architecture scalable to large network sizes. We further propose a method called Hybrid Risk-Mitigating Architectural Search (HRMAS) to systematically optimize the topology of the proposed recurrent motifs and SC-ML layer architecture. HRMAS is an alternating two-step optimization process by which we mitigate the risk of network instability and performance degradation caused by architectural change by introducing a novel biologically-inspired "self-repairing" mechanism through intrinsic plasticity. The intrinsic plasticity is introduced to the second step of each HRMAS iteration and acts as unsupervised fast self-adaptation to structural and synaptic weight modifications introduced by the first step during the RSNN architectural "evolution." We demonstrate that the proposed automatic architecture optimization leads to significant performance gains over existing manually designed RSNNs: we achieve 96.44% on TI46-Alpha, 94.66% on N-TIDIGITS, 90.28% on DVS-Gesture, and 98.72% on N-MNIST. To the best of the authors' knowledge, this is the first work to perform systematic architecture optimization on RSNNs.

Emerging opportunities and challenges for the future of reservoir computing

Reservoir computing originates in the early 2000s, the core idea being to utilize dynamical systems as reservoirs (nonlinear generalizations of standard bases) to adaptively learn spatiotemporal features and hidden patterns in complex time series. Shown to have the potential of achieving higher-precision prediction in chaotic systems, those pioneering works led to a great amount of interest and follow-ups in the community of nonlinear dynamics and complex systems. To unlock the full capabilities of reservoir computing towards a fast, lightweight, and significantly more interpretable learning framework for temporal dynamical systems, substantially more research is needed. This Perspective intends to elucidate the parallel progress of mathematical theory, algorithm design and experimental realizations of reservoir computing, and identify emerging opportunities as well as existing challenges for large-scale industrial adoption of reservoir computing, together with a few ideas and viewpoints on how some of those challenges might be resolved with joint efforts by academic and industrial researchers across multiple disciplines.

SHIP: a computational framework for simulating and validating novel technologies in hardware spiking neural networks

Investigations in the field of spiking neural networks (SNNs) encompass diverse, yet overlapping, scientific disciplines. Examples range from purely neuroscientific investigations, researches on computational aspects of neuroscience, or applicative-oriented studies aiming to improve SNNs performance or to develop artificial hardware counterparts. However, the simulation of SNNs is a complex task that can not be adequately addressed with a single platform applicable to all scenarios. The optimization of a simulation environment to meet specific metrics often entails compromises in other aspects. This computational challenge has led to an apparent dichotomy of approaches, with model-driven algorithms dedicated to the detailed simulation of biological networks, and data-driven algorithms designed for efficient processing of large input datasets. Nevertheless, material scientists, device physicists, and neuromorphic engineers who develop new technologies for spiking neuromorphic hardware solutions would find benefit in a simulation environment that borrows aspects from both approaches, thus facilitating modeling, analysis, and training of prospective SNN systems. This manuscript explores the numerical challenges deriving from the simulation of spiking neural networks, and introduces SHIP, Spiking (neural network) Hardware In PyTorch, a numerical tool that supports the investigation and/or validation of materials, devices, small circuit blocks within SNN architectures. SHIP facilitates the algorithmic definition of the models for the components of a network, the monitoring of states and output of the modeled systems, and the training of the synaptic weights of the network, by way of user-defined unsupervised learning rules or supervised training techniques derived from conventional machine learning. SHIP offers a valuable tool for researchers and developers in the field of hardware-based spiking neural networks, enabling efficient simulation and validation of novel technologies.

Improving Multispike Learning With Plastic Synaptic Delays

Emulating the spike-based processing in the brain, spiking neural networks (SNNs) are developed and act as a promising candidate for the new generation of artificial neural networks that aim to produce efficient cognitions as the brain. Due to the complex dynamics and nonlinearity of SNNs, designing efficient learning algorithms has remained a major difficulty, which attracts great research attention. Most existing ones focus on the adjustment of synaptic weights. However, other components, such as synaptic delays, are found to be adaptive and important in modulating neural behavior. How could plasticity on different components cooperate to improve the learning of SNNs remains as an interesting question. Advancing our previous multispike learning, we propose a new joint weight-delay plasticity rule, named TDP-DL, in this article. Plastic delays are integrated into the learning framework, and as a result, the performance of multispike learning is significantly improved. Simulation results highlight the effectiveness and efficiency of our TDP-DL rule compared to baseline ones. Moreover, we reveal the underlying principle of how synaptic weights and delays cooperate with each other through a synthetic task of interval selectivity and show that plastic delays can enhance the selectivity and flexibility of neurons by shifting information across time. Due to this capability, useful information distributed away in the time domain can be effectively integrated for a better accuracy performance, as highlighted in our generalization tasks of the image, speech, and event-based object recognitions. Our work is thus valuable and significant to improve the performance of spike-based neuromorphic computing.

Handwritten digit recognition by spin waves in a Skyrmion reservoir

By performing numerical simulations for the handwritten digit recognition task, we demonstrate that a magnetic skyrmion lattice confined in a thin-plate magnet possesses high capability of reservoir computing. We obtain a high recognition rate of more than 88%, higher by about 10% than a baseline taken as the echo state network model. We find that this excellent performance arises from enhanced nonlinearity in the transformation which maps the input data onto an information space with higher dimensions, carried by interferences of spin waves in the skyrmion lattice. Because the skyrmions require only application of static magnetic field instead of nanofabrication for their creation in contrast to other spintronics reservoirs, our result consolidates the high potential of skyrmions for application to reservoir computing devices.

Adaptive structure evolution and biologically plausible synaptic plasticity for recurrent spiking neural networks

The architecture design and multi-scale learning principles of the human brain that evolved over hundreds of millions of years are crucial to realizing human-like intelligence. Spiking neural network based Liquid State Machine (LSM) serves as a suitable architecture to study brain-inspired intelligence because of its brain-inspired structure and the potential for integrating multiple biological principles. Existing researches on LSM focus on different certain perspectives, including high-dimensional encoding or optimization of the liquid layer, network architecture search, and application to hardware devices. There is still a lack of in-depth inspiration from the learning and structural evolution mechanism of the brain. Considering these limitations, this paper presents a novel LSM learning model that integrates adaptive structural evolution and multi-scale biological learning rules. For structural evolution, an adaptive evolvable LSM model is developed to optimize the neural architecture design of liquid layer with separation property. For brain-inspired learning of LSM, we propose a dopamine-modulated Bienenstock-Cooper-Munros (DA-BCM) method that incorporates global long-term dopamine regulation and local trace-based BCM synaptic plasticity. Comparative experimental results on different decision-making tasks show that introducing structural evolution of the liquid layer, and the DA-BCM regulation of the liquid layer and the readout layer could improve the decision-making ability of LSM and flexibly adapt to rule reversal. This work is committed to exploring how evolution can help to design more appropriate network architectures and how multi-scale neuroplasticity principles coordinated to enable the optimization and learning of LSMs for relatively complex decision-making tasks.

Comparison and Selection of Spike Encoding Algorithms for SNN on FPGA

The information in Spiking Neural Networks (SNNs) is carried by discrete spikes. Therefore, the conversion between the spiking signals and real-value signals has an important impact on the encoding efficiency and performance of SNNs, which is usually completed by spike encoding algorithms. In order to select suitable spike encoding algorithms for different SNNs, this work evaluates four commonly used spike encoding algorithms. The evaluation is based on the FPGA implementation results of the algorithms, including calculation speed, resource consumption, accuracy, and anti-noiseability, so as to better adapt to the neuromorphic implementation of SNN. Two real-world applicaitons are also used to verify the evaluation results. By analyzing and comparing the evaluation results, this work summarizes the characteristics and application range of different algorithms. In general, the sliding window algorithm has relatively low accuracy and is suitable for observing signal trends. Pulsewidth modulated-Based algorithm and step-forward algorithm are suitable for accurate reconstruction of various signals except for square wave signals, while Ben's Spiker algorithm can remedy this. Finally, a scoring method that can be used for spiking coding algorithm selection is proposed, which can help to improve the encoding efficiency of neuromorphic SNNs.

Tuning Convolutional Spiking Neural Network With Biologically Plausible Reward Propagation

Spiking neural networks (SNNs) contain more biologically realistic structures and biologically inspired learning principles than those in standard artificial neural networks (ANNs). SNNs are considered the third generation of ANNs, powerful on the robust computation with a low computational cost. The neurons in SNNs are nondifferential, containing decayed historical states and generating event-based spikes after their states reaching the firing threshold. These dynamic characteristics of SNNs make it difficult to be directly trained with the standard backpropagation (BP), which is also considered not biologically plausible. In this article, a biologically plausible reward propagation (BRP) algorithm is proposed and applied to the SNN architecture with both spiking-convolution (with both 1-D and 2-D convolutional kernels) and full-connection layers. Unlike the standard BP that propagates error signals from postsynaptic to presynaptic neurons layer by layer, the BRP propagates target labels instead of errors directly from the output layer to all prehidden layers. This effort is more consistent with the top-down reward-guiding learning in cortical columns of the neocortex. Synaptic modifications with only local gradient differences are induced with pseudo-BP that might also be replaced with the spike-timing-dependent plasticity (STDP). The performance of the proposed BRP-SNN is further verified on the spatial (including MNIST and Cifar-10) and temporal (including TIDigits and DvsGesture) tasks, where the SNN using BRP has reached a similar accuracy compared to other state-of-the-art (SOTA) BP-based SNNs and saved 50% more computational cost than ANNs. We think that the introduction of biologically plausible learning rules to the training procedure of biologically realistic SNNs will give us more hints and inspiration toward a better understanding of the biological system's intelligent nature.

Recognizing intertwined patterns using a network of spiking pattern recognition platforms

Artificial intelligence computing adapted from biology is a suitable platform for the development of intelligent machines by imitating the functional mechanisms of the nervous system in creating high-level activities such as learning, decision making and cognition in today's systems. Here, the concentration is on improvement the cognitive potential of artificial intelligence network with a bio-inspired structure. In this regard, four spiking pattern recognition platforms for recognizing digits and letters of EMNIST, patterns of YALE, and ORL datasets are proposed. All networks are developed based on a similar structure in the input image coding, model of neurons (pyramidal neurons and interneurons) and synapses (excitatory AMPA and inhibitory GABA currents), and learning procedure. Networks 1-4 are trained on Digits, Letters, faces of YALE and ORL, respectively, with the proposed un-supervised, spatial-temporal, and sparse spike-based learning mechanism based on the biological observation of the brain learning. When the networks have reached the highest recognition accuracy in the relevant patterns, the main goal of the article, which is to achieve high-performance pattern recognition system with higher cognitive ability, is followed. The pattern recognition network that is able to detect the combination of multiple patterns which called intertwined patterns has not been discussed yet. Therefore, by integrating four trained spiking pattern recognition platforms in one system configuration, we are able to recognize intertwined patterns. These results are presented for the first time and could be the pioneer of a new generation of pattern recognition networks with a significant ability in smart machines.

Optimizing the Neural Structure and Hyperparameters of Liquid State Machines Based on Evolutionary Membrane Algorithm

As one of the important artificial intelligence fields, brain-like computing attempts to give machines a higher intelligence level by studying and simulating the cognitive principles of the human brain. A spiking neural network (SNN) is one of the research directions of brain-like computing, characterized by better biogenesis and stronger computing power than the traditional neural network. A liquid state machine (LSM) is a neural computing model with a recurrent network structure based on SNN. In this paper, a learning algorithm based on an evolutionary membrane algorithm is proposed to optimize the neural structure and hyperparameters of an LSM. First, the object of the proposed algorithm is designed according to the neural structure and hyperparameters of the LSM. Second, the reaction rules of the proposed algorithm are employed to discover the best neural structure and hyperparameters of the LSM. Third, the membrane structure is that the skin membrane contains several elementary membranes to speed up the search of the proposed algorithm. In the simulation experiment, effectiveness verification is carried out on the MNIST and KTH datasets. In terms of the MNIST datasets, the best test results of the proposed algorithm with 500, 1000 and 2000 spiking neurons are 86.8%, 90.6% and 90.8%, respectively. The best test results of the proposed algorithm on KTH with 500, 1000 and 2000 spiking neurons are 82.9%, 85.3% and 86.3%, respectively. The simulation results show that the proposed algorithm has a more competitive advantage than other experimental algorithms.

FangTianSim: High-Level Cycle-Accurate Resistive Random-Access Memory-Based Multi-Core Spiking Neural Network Processor Simulator

Realization of spiking neural network (SNN) hardware with high energy efficiency and high integration may provide a promising solution to data processing challenges in future internet of things (IoT) and artificial intelligence (AI). Recently, design of multi-core reconfigurable SNN chip based on resistive random-access memory (RRAM) is drawing great attention, owing to the unique properties of RRAM, e.g., high integration density, low power consumption, and processing-in-memory (PIM). Therefore, RRAM-based SNN chip may have further improvements in integration and energy efficiency. The design of such a chip will face the following problems: significant delay in pulse transmission due to complex logic control and inter-core communication; high risk of digital, analog, and RRAM hybrid design; and non-ideal characteristics of analog circuit and RRAM. In order to effectively bridge the gap between device, circuit, algorithm, and architecture, this paper proposes a simulation model—FangTianSim, which covers analog neuron circuit, RRAM model and multi-core architecture and its accuracy is at the clock level. This model can be used to verify the functionalities, delay, and power consumption of SNN chip. This information cannot only be used to verify the rationality of the architecture but also guide the chip design. In order to map different network topologies on the chip, SNN representation format, interpreter, and instruction generator are designed. Finally, the function of FangTianSim is verified on liquid state machine (LSM), fully connected neural network (FCNN), and convolutional neural network (CNN).

ES-ImageNet: A Million Event-Stream Classification Dataset for Spiking Neural Networks

With event-driven algorithms, especially spiking neural networks (SNNs), achieving continuous improvement in neuromorphic vision processing, a more challenging event-stream dataset is urgently needed. However, it is well-known that creating an ES-dataset is a time-consuming and costly task with neuromorphic cameras like dynamic vision sensors (DVS). In this work, we propose a fast and effective algorithm termed Omnidirectional Discrete Gradient (ODG) to convert the popular computer vision dataset ILSVRC2012 into its event-stream (ES) version, generating about 1,300,000 frame-based images into ES-samples in 1,000 categories. In this way, we propose an ES-dataset called ES-ImageNet, which is dozens of times larger than other neuromorphic classification datasets at present and completely generated by the software. The ODG algorithm implements image motion to generate local value changes with discrete gradient information in different directions, providing a low-cost and high-speed method for converting frame-based images into event streams, along with Edge-Integral to reconstruct the high-quality images from event streams. Furthermore, we analyze the statistics of ES-ImageNet in multiple ways, and a performance benchmark of the dataset is also provided using both famous deep neural network algorithms and spiking neural network algorithms. We believe that this work shall provide a new large-scale benchmark dataset for SNNs and neuromorphic vision.

Biologically-Inspired Pulse Signal Processing for Intelligence at the Edge

There is an ever-growing mismatch between the proliferation of data-intensive, power-hungry deep learning solutions in the machine learning (ML) community and the need for agile, portable solutions in resource-constrained devices, particularly for intelligence at the edge. In this paper, we present a fundamentally novel approach that leverages data-driven intelligence with biologically-inspired efficiency. The proposed Sparse Embodiment Neural-Statistical Architecture (SENSA) decomposes the learning task into two distinct phases: a training phase and a hardware embedment phase where prototypes are extracted from the trained network and used to construct fast, sparse embodiment for hardware deployment at the edge. Specifically, we propose the Sparse Pulse Automata via Reproducing Kernel (SPARK) method, which first constructs a learning machine in the form of a dynamical system using energy-efficient spike or pulse trains, commonly used in neuroscience and neuromorphic engineering, then extracts a rule-based solution in the form of automata or lookup tables for rapid deployment in edge computing platforms. We propose to use the theoretically-grounded unifying framework of the Reproducing Kernel Hilbert Space (RKHS) to provide interpretable, nonlinear, and nonparametric solutions, compared to the typical neural network approach. In kernel methods, the explicit representation of the data is of secondary nature, allowing the same algorithm to be used for different data types without altering the learning rules. To showcase SPARK’s capabilities, we carried out the first proof-of-concept demonstration on the task of isolated-word automatic speech recognition (ASR) or keyword spotting, benchmarked on the TI-46 digit corpus. Together, these energy-efficient and resource-conscious techniques will bring advanced machine learning solutions closer to the edge.

Neuronal-Plasticity and Reward-Propagation Improved Recurrent Spiking Neural Networks

Different types of dynamics and plasticity principles found through natural neural networks have been well-applied on Spiking neural networks (SNNs) because of their biologically-plausible efficient and robust computations compared to their counterpart deep neural networks (DNNs). Here, we further propose a special Neuronal-plasticity and Reward-propagation improved Recurrent SNN (NRR-SNN). The historically-related adaptive threshold with two channels is highlighted as important neuronal plasticity for increasing the neuronal dynamics, and then global labels instead of errors are used as a reward for the paralleling gradient propagation. Besides, a recurrent loop with proper sparseness is designed for robust computation. Higher accuracy and stronger robust computation are achieved on two sequential datasets (i.e., TIDigits and TIMIT datasets), which to some extent, shows the power of the proposed NRR-SNN with biologically-plausible improvements.

A new recursive least squares-based learning algorithm for spiking neurons

Spiking neural networks (SNNs) are regarded as effective models for processing spatio-temporal information. However, their inherent complexity of temporal coding makes it an arduous task to put forward an effective supervised learning algorithm, which still puzzles researchers in this area. In this paper, we propose a Recursive Least Squares-Based Learning Rule (RLSBLR) for SNN to generate the desired spatio-temporal spike train. During the learning process of our method, the weight update is driven by the cost function defined by the difference between the membrane potential and the firing threshold. The amount of weight modification depends not only on the impact of the current error function, but also on the previous error functions which are evaluated by current weights. In order to improve the learning performance, we integrate a modified synaptic delay learning to the proposed RLSBLR. We conduct experiments in different settings, such as spiking lengths, number of inputs, firing rates, noises and learning parameters, to thoroughly investigate the performance of this learning algorithm. The proposed RLSBLR is compared with competitive algorithms of Perceptron-Based Spiking Neuron Learning Rule (PBSNLR) and Remote Supervised Method (ReSuMe). Experimental results demonstrate that the proposed RLSBLR can achieve higher learning accuracy, higher efficiency and better robustness against different types of noise. In addition, we apply the proposed RLSBLR to open source database TIDIGITS, and the results show that our algorithm has a good practical application performance.

Distributed Training for Multi-Layer Neural Networks by Consensus

Over the past decade, there has been a growing interest in large-scale and privacy-concerned machine learning, especially in the situation where the data cannot be shared due to privacy protection or cannot be centralized due to computational limitations. Parallel computation has been proposed to circumvent these limitations, usually based on the master-slave and decentralized topologies, and the comparison study shows that a decentralized graph could avoid the possible communication jam on the central agent but incur extra communication cost. In this brief, a consensus algorithm is designed to allow all agents over the decentralized graph to converge to each other, and the distributed neural networks with enough consensus steps could have nearly the same performance as the centralized training model. Through the analysis of convergence, it is proved that all agents over an undirected graph could converge to the same optimal model even with only a single consensus step, and this can significantly reduce the communication cost. Simulation studies demonstrate that the proposed distributed training algorithm for multi-layer neural networks without data exchange could exhibit comparable or even better performance than the centralized training model.

Evolving Local Plasticity Rules for Synergistic Learning in Echo State Networks

Existing synaptic plasticity rules for optimizing the connections between neurons within the reservoir of echo state networks (ESNs) remain to be global in that the same type of plasticity rule with the same parameters is applied to all neurons. However, this is biologically implausible and practically inflexible for learning the structures in the input signals, thereby limiting the learning performance of ESNs. In this paper, we propose to use local plasticity rules that allow different neurons to use different types of plasticity rules and different parameters, which are achieved by optimizing the parameters of the local plasticity rules using the evolution strategy (ES) with covariance matrix adaptation (CMA-ES). We show that evolving neural plasticity will result in a synergistic learning of different plasticity rules, which plays an important role in improving the learning performance. Meanwhile, we show that the local plasticity rules can effectively alleviate synaptic interferences in learning the structure in sensory inputs. The proposed local plasticity rules are compared with a number of the state-of-the-art ESN models and the canonical ESN using a global plasticity rule on a set of widely used prediction and classification benchmark problems to demonstrate its competitive learning performance.

Deep Spiking Neural Networks for Large Vocabulary Automatic Speech Recognition

Artificial neural networks (ANN) have become the mainstream acoustic modeling technique for large vocabulary automatic speech recognition (ASR). A conventional ANN features a multi-layer architecture that requires massive amounts of computation. The brain-inspired spiking neural networks (SNN) closely mimic the biological neural networks and can operate on low-power neuromorphic hardware with spike-based computation. Motivated by their unprecedented energy-efficiency and rapid information processing capability, we explore the use of SNNs for speech recognition. In this work, we use SNNs for acoustic modeling and evaluate their performance on several large vocabulary recognition scenarios. The experimental results demonstrate competitive ASR accuracies to their ANN counterparts, while require only 10 algorithmic time steps and as low as 0.68 times total synaptic operations to classify each audio frame. Integrating the algorithmic power of deep SNNs with energy-efficient neuromorphic hardware, therefore, offer an attractive solution for ASR applications running locally on mobile and embedded devices.

Boosting Throughput and Efficiency of Hardware Spiking Neural Accelerators Using Time Compression Supporting Multiple Spike Codes

Spiking neural networks (SNNs) are the third generation of neural networks and can explore both rate and temporal coding for energy-efficient event-driven computation. However, the decision accuracy of existing SNN designs is contingent upon processing a large number of spikes over a long period. Nevertheless, the switching power of SNN hardware accelerators is proportional to the number of spikes processed while the length of spike trains limits throughput and static power efficiency. This paper presents the first study on developing temporal compression to significantly boost throughput and reduce energy dissipation of digital hardware SNN accelerators while being applicable to multiple spike codes. The proposed compression architectures consist of low-cost input spike compression units, novel input-and-output-weighted spiking neurons, and reconfigurable time constant scaling to support large and flexible time compression ratios. Our compression architectures can be transparently applied to any given pre-designed SNNs employing either rate or temporal codes while incurring minimal modification of the neural models, learning algorithms, and hardware design. Using spiking speech and image recognition datasets, we demonstrate the feasibility of supporting large time compression ratios of up to 16×, delivering up to 15.93×, 13.88×, and 86.21× improvements in throughput, energy dissipation, the tradeoffs between hardware area, runtime, energy, and classification accuracy, respectively based on different spike codes on a Xilinx Zynq-7000 FPGA. These results are achieved while incurring little extra hardware overhead.

An Efficient and Perceptually Motivated Auditory Neural Encoding and Decoding Algorithm for Spiking Neural Networks

The auditory front-end is an integral part of a spiking neural network (SNN) when performing auditory cognitive tasks. It encodes the temporal dynamic stimulus, such as speech and audio, into an efficient, effective and reconstructable spike pattern to facilitate the subsequent processing. However, most of the auditory front-ends in current studies have not made use of recent findings in psychoacoustics and physiology concerning human listening. In this paper, we propose a neural encoding and decoding scheme that is optimized for audio processing. The neural encoding scheme, that we call Biologically plausible Auditory Encoding (BAE), emulates the functions of the perceptual components of the human auditory system, that include the cochlear filter bank, the inner hair cells, auditory masking effects from psychoacoustic models, and the spike neural encoding by the auditory nerve. We evaluate the perceptual quality of the BAE scheme using PESQ; the performance of the BAE based on sound classification and speech recognition experiments. Finally, we also built and published two spike-version of speech datasets: the Spike-TIDIGITS and the Spike-TIMIT, for researchers to use and benchmarking of future SNN research.

Privacy-enhanced multi-party deep learning

In multi-party deep learning, multiple participants jointly train a deep learning model through a central server to achieve common objectives without sharing their private data. Recently, a significant amount of progress has been made toward the privacy issue of this emerging multi-party deep learning paradigm. In this paper, we mainly focus on two problems in multi-party deep learning. The first problem is that most of the existing works are incapable of defending simultaneously against the attacks of honest-but-curious participants and an honest-but-curious server without a manager trusted by all participants. To tackle this problem, we design a privacy-enhanced multi-party deep learning framework, which integrates differential privacy and homomorphic encryption to prevent potential privacy leakage to other participants and a central server without requiring a manager that all participants trust. The other problem is that existing frameworks consume high total privacy budget when applying differential privacy for preserving privacy, which leads to a high risk of privacy leakage. In order to alleviate this problem, we propose three strategies for dynamically allocating privacy budget at each epoch to further enhance privacy guarantees without compromising the model utility. Moreover, it provides participants with an intuitive handle to strike a balance between the privacy level and the training efficiency by choosing different strategies. Both analytical and experimental evaluations demonstrate the promising performance of our proposed framework.

A Novel Equivalent Model of Active Distribution Networks Based on LSTM

Dynamic behaviors of distribution networks are of great importance for the power system analysis. Nowadays, due to the integration of the renewable energy generation, energy storage, plug-in electric vehicles, and distribution networks turn from passive systems to active ones. Hence, the dynamic behaviors of active distribution networks (ADNs) are much more complex than the traditional ones. The research interests how to establish an accurate model of ADNs in modern power systems are drawing a great deal of attention. In this paper, motivated by the similarities between power system differential algebraic equations and the forward calculation flows of recurrent neural networks (RNNs), a long short-term memory (LSTM) RNN-based equivalent model is proposed to accurately represent the ADNs. First, the adoption reasons of the proposed LSTM RNN-based equivalent model are explained, and its advantages are analyzed from the mathematical point of view. Then, the accuracy and generalization performance of the proposed model is evaluated using the IEEE 39-Bus New England system integrated with ADNs in the study cases. It reveals that the proposed LSTM RNN-based equivalent model has a generalization capability to capture the dynamic behaviors of ADNs with high accuracy.

Pattern Classification by Spiking Neural Networks Combining Self-Organized and Reward-Related Spike-Timing-Dependent Plasticity

Many recent studies have applied to spike neural networks with spike-timing-dependent plasticity (STDP) to machine learning problems. The learning abilities of dopamine-modulated STDP (DA-STDP) for reward-related synaptic plasticity have also been gathering attention. Following these studies, we hypothesize that a network structure combining self-organized STDP and reward-related DA-STDP can solve the machine learning problem of pattern classification. Therefore, we studied the ability of a network in which recurrent spiking neural networks are combined with STDP for non-supervised learning, with an output layer joined by DA-STDP for supervised learning, to perform pattern classification. We confirmed that this network could perform pattern classification using the STDP effect for emphasizing features of the input spike pattern and DA-STDP supervised learning. Therefore, our proposed spiking neural network may prove to be a useful approach for machine learning problems.

First Error-Based Supervised Learning Algorithm for Spiking Neural Networks

Neural circuits respond to multiple sensory stimuli by firing precisely timed spikes. Inspired by this phenomenon, the spike timing-based spiking neural networks (SNNs) are proposed to process and memorize the spatiotemporal spike patterns. However, the response speed and accuracy of the existing learning algorithms of SNNs are still lacking compared to the human brain. To further improve the performance of learning precisely timed spikes, we propose a new weight updating mechanism which always adjusts the synaptic weights at the first wrong output spike time. The proposed learning algorithm can accurately adjust the synaptic weights that contribute to the membrane potential of desired and non-desired firing time. Experimental results demonstrate that the proposed algorithm shows higher accuracy, better robustness, and less computational resources compared with the remote supervised method (ReSuMe) and the spike pattern association neuron (SPAN), which are classic sequence learning algorithms. In addition, the SNN-based computational model equipped with the proposed learning method achieves better recognition results in speech recognition task compared with other bio-inspired baseline systems.

On the Universality of Memcomputing Machines

Universal memcomputing machines (UMMs) represent a novel computational model in which memory (time nonlocality) accomplishes both tasks of storing and processing of information. UMMs have been shown to be Turing-complete, namely, they can simulate any Turing machine. In this paper, we first introduce a novel set theory approach to compare different computational models and use it to recover the previous results on Turing-completeness of UMMs. We then relate UMMs directly to liquid-state machines (or "reservoir-computing") and quantum machines ("quantum computing"). We show that UMMs can simulate both types of machines, hence they are both "liquid-" or "reservoir-complete" and "quantum-complete." Of course, these statements pertain only to the type of problems these machines can solve and not to the amount of resources required for such simulations. Nonetheless, the set-theoretic method presented here provides a general framework which describes the relationship between any computational models.

Artificial Neuron and Synapse Realized in an Antiferromagnet/Ferromagnet Heterostructure Using Dynamics of Spin-Orbit Torque Switching

Efficient information processing in the human brain is achieved by dynamics of neurons and synapses, motivating effective implementation of artificial spiking neural networks. Here, the dynamics of spin-orbit torque switching in antiferromagnet/ferromagnet heterostructures is studied to show the capability of the material system to form artificial neurons and synapses for asynchronous spiking neural networks. The magnetization switching, driven by a single current pulse or trains of pulses, is examined as a function of the pulse width (1 s to 1 ns), amplitude, number, and pulse-to-pulse interval. Based on this dynamics and the unique ability of the system to exhibit binary or analog behavior depending on the device size, key functionalities of a synapse (spike-timing-dependent plasticity) and a neuron (leaky integrate-and-fire) are reproduced in the same material and on the basis of the same working principle. These results open a way toward spintronics-based neuromorphic hardware that executes cognitive tasks with the efficiency of the human brain.

Analysis of Liquid Ensembles for Enhancing the Performance and Accuracy of Liquid State Machines

Liquid state machine (LSM), a bio-inspired computing model consisting of the input sparsely connected to a randomly interlinked reservoir (or liquid) of spiking neurons followed by a readout layer, finds utility in a range of applications varying from robot control and sequence generation to action, speech, and image recognition. LSMs stand out among other Recurrent Neural Network (RNN) architectures due to their simplistic structure and lower training complexity. Plethora of recent efforts have been focused toward mimicking certain characteristics of biological systems to enhance the performance of modern artificial neural networks. It has been shown that biological neurons are more likely to be connected to other neurons in the close proximity, and tend to be disconnected as the neurons are spatially far apart. Inspired by this, we propose a group of locally connected neuron reservoirs, or an ensemble of liquids approach, for LSMs. We analyze how the segmentation of a single large liquid to create an ensemble of multiple smaller liquids affects the latency and accuracy of an LSM. In our analysis, we quantify the ability of the proposed ensemble approach to provide an improved representation of the input using the Separation Property (SP) and Approximation Property (AP). Our results illustrate that the ensemble approach enhances class discrimination (quantified as the ratio between the SP and AP), leading to better accuracy in speech and image recognition tasks, when compared to a single large liquid. Furthermore, we obtain performance benefits in terms of improved inference time and reduced memory requirements, due to lowered number of connections and the freedom to parallelize the liquid evaluation process.

Recent advances in physical reservoir computing: A review

Reservoir computing is a computational framework suited for temporal/sequential data processing. It is derived from several recurrent neural network models, including echo state networks and liquid state machines. A reservoir computing system consists of a reservoir for mapping inputs into a high-dimensional space and a readout for pattern analysis from the high-dimensional states in the reservoir. The reservoir is fixed and only the readout is trained with a simple method such as linear regression and classification. Thus, the major advantage of reservoir computing compared to other recurrent neural networks is fast learning, resulting in low training cost. Another advantage is that the reservoir without adaptive updating is amenable to hardware implementation using a variety of physical systems, substrates, and devices. In fact, such physical reservoir computing has attracted increasing attention in diverse fields of research. The purpose of this review is to provide an overview of recent advances in physical reservoir computing by classifying them according to the type of the reservoir. We discuss the current issues and perspectives related to physical reservoir computing, in order to further expand its practical applications and develop next-generation machine learning systems.

Information-Theoretic Intrinsic Plasticity for Online Unsupervised Learning in Spiking Neural Networks

As a self-adaptive mechanism, intrinsic plasticity (IP) plays an essential role in maintaining homeostasis and shaping the dynamics of neural circuits. From a computational point of view, IP has the potential to enable promising non-Hebbian learning in artificial neural networks. While IP based learning has been attempted for spiking neuron models, the existing IP rules are ad hoc in nature, and the practical success of their application has not been demonstrated particularly toward enabling real-life learning tasks. This work aims to address the theoretical and practical limitations of the existing works by proposing a new IP rule named SpiKL-IP. SpiKL-IP is developed based on a rigorous information-theoretic approach where the target of IP tuning is to maximize the entropy of the output firing rate distribution of each spiking neuron. This goal is achieved by tuning the output firing rate distribution toward a targeted optimal exponential distribution. Operating on a proposed firing-rate transfer function, SpiKL-IP adapts the intrinsic parameters of a spiking neuron while minimizing the KL-divergence from the targeted exponential distribution to the actual output firing rate distribution. SpiKL-IP can robustly operate in an online manner under complex inputs and network settings. Simulation studies demonstrate that the application of SpiKL-IP to individual neurons in isolation or as part of a larger spiking neural network robustly produces the desired exponential distribution. The evaluation of SpiKL-IP under real-world speech and image classification tasks shows that SpiKL-IP noticeably outperforms two existing IP rules and can significantly boost recognition accuracy by up to more than 16%.

Unsupervised speech recognition through spike-timing-dependent plasticity in a convolutional spiking neural network

Speech recognition (SR) has been improved significantly by artificial neural networks (ANNs), but ANNs have the drawbacks of biologically implausibility and excessive power consumption because of the nonlocal transfer of real-valued errors and weights. While spiking neural networks (SNNs) have the potential to solve these drawbacks of ANNs due to their efficient spike communication and their natural way to utilize kinds of synaptic plasticity rules found in brain for weight modification. However, existing SNN models for SR either had bad performance, or were trained in biologically implausible ways. In this paper, we present a biologically inspired convolutional SNN model for SR. The network adopts the time-to-first-spike coding scheme for fast and efficient information processing. A biological learning rule, spike-timing-dependent plasticity (STDP), is used to adjust the synaptic weights of convolutional neurons to form receptive fields in an unsupervised way. In the convolutional structure, the strategy of local weight sharing is introduced and could lead to better feature extraction of speech signals than global weight sharing. We first evaluated the SNN model with a linear support vector machine (SVM) on the TIDIGITS dataset and it got the performance of 97.5%, comparable to the best results of ANNs. Deep analysis on network outputs showed that, not only are the output data more linearly separable, but they also have fewer dimensions and become sparse. To further confirm the validity of our model, we trained it on a more difficult recognition task based on the TIMIT dataset, and it got a high performance of 93.8%. Moreover, a linear spike-based classifier-tempotron-can also achieve high accuracies very close to that of SVM on both the two tasks. These demonstrate that an STDP-based convolutional SNN model equipped with local weight sharing and temporal coding is capable of solving the SR task accurately and efficiently.

A Spiking Neural Network Framework for Robust Sound Classification

Environmental sounds form part of our daily life. With the advancement of deep learning models and the abundance of training data, the performance of automatic sound classification (ASC) systems has improved significantly in recent years. However, the high computational cost, hence high power consumption, remains a major hurdle for large-scale implementation of ASC systems on mobile and wearable devices. Motivated by the observations that humans are highly effective and consume little power whilst analyzing complex audio scenes, we propose a biologically plausible ASC framework, namely SOM-SNN. This framework uses the unsupervised self-organizing map (SOM) for representing frequency contents embedded within the acoustic signals, followed by an event-based spiking neural network (SNN) for spatiotemporal spiking pattern classification. We report experimental results on the RWCP environmental sound and TIDIGITS spoken digits datasets, which demonstrate competitive classification accuracies over other deep learning and SNN-based models. The SOM-SNN framework is also shown to be highly robust to corrupting noise after multi-condition training, whereby the model is trained with noise-corrupted sound samples. Moreover, we discover the early decision making capability of the proposed framework: an accurate classification can be made with an only partial presentation of the input.

Deep Learning With Spiking Neurons: Opportunities and Challenges

Spiking neural networks (SNNs) are inspired by information processing in biology, where sparse and asynchronous binary signals are communicated and processed in a massively parallel fashion. SNNs on neuromorphic hardware exhibit favorable properties such as low power consumption, fast inference, and event-driven information processing. This makes them interesting candidates for the efficient implementation of deep neural networks, the method of choice for many machine learning tasks. In this review, we address the opportunities that deep spiking networks offer and investigate in detail the challenges associated with training SNNs in a way that makes them competitive with conventional deep learning, but simultaneously allows for efficient mapping to hardware. A wide range of training methods for SNNs is presented, ranging from the conversion of conventional deep networks into SNNs, constrained training before conversion, spiking variants of backpropagation, and biologically motivated variants of STDP. The goal of our review is to define a categorization of SNN training methods, and summarize their advantages and drawbacks. We further discuss relationships between SNNs and binary networks, which are becoming popular for efficient digital hardware implementation. Neuromorphic hardware platforms have great potential to enable deep spiking networks in real-world applications. We compare the suitability of various neuromorphic systems that have been developed over the past years, and investigate potential use cases. Neuromorphic approaches and conventional machine learning should not be considered simply two solutions to the same classes of problems, instead it is possible to identify and exploit their task-specific advantages. Deep SNNs offer great opportunities to work with new types of event-based sensors, exploit temporal codes and local on-chip learning, and we have so far just scratched the surface of realizing these advantages in practical applications.

Biologically-Inspired Spike-Based Automatic Speech Recognition of Isolated Digits Over a Reproducing Kernel Hilbert Space

This paper presents a novel real-time dynamic framework for quantifying time-series structure in spoken words using spikes. Audio signals are converted into multi-channel spike trains using a biologically-inspired leaky integrate-and-fire (LIF) spike generator. These spike trains are mapped into a function space of infinite dimension, i.e., a Reproducing Kernel Hilbert Space (RKHS) using point-process kernels, where a state-space model learns the dynamics of the multidimensional spike input using gradient descent learning. This kernelized recurrent system is very parsimonious and achieves the necessary memory depth via feedback of its internal states when trained discriminatively, utilizing the full context of the phoneme sequence. A main advantage of modeling nonlinear dynamics using state-space trajectories in the RKHS is that it imposes no restriction on the relationship between the exogenous input and its internal state. We are free to choose the input representation with an appropriate kernel, and changing the kernel does not impact the system nor the learning algorithm. Moreover, we show that this novel framework can outperform both traditional hidden Markov model (HMM) speech processing as well as neuromorphic implementations based on spiking neural network (SNN), yielding accurate and ultra-low power word spotters. As a proof of concept, we demonstrate its capabilities using the benchmark TI-46 digit corpus for isolated-word automatic speech recognition (ASR) or keyword spotting. Compared to HMM using Mel-frequency cepstral coefficient (MFCC) front-end without time-derivatives, our MFCC-KAARMA offered improved performance. For spike-train front-end, spike-KAARMA also outperformed state-of-the-art SNN solutions. Furthermore, compared to MFCCs, spike trains provided enhanced noise robustness in certain low signal-to-noise ratio (SNR) regime.

Anytime multipurpose emotion recognition from EEG data using a Liquid State Machine based framework

Recent technological advances in machine learning offer the possibility of decoding complex datasets and discern latent patterns. In this study, we adopt Liquid State Machines (LSM) to recognize the emotional state of an individual based on EEG data. LSM were applied to a previously validated EEG dataset where subjects view a battery of emotional film clips and then rate their degree of emotion during each film based on valence, arousal, and liking levels. We introduce LSM as a model for an automatic feature extraction and prediction from raw EEG with potential extension to a wider range of applications. We also elaborate on how to exploit the separation property in LSM to build a multipurpose and anytime recognition framework, where we used one trained model to predict valence, arousal and liking levels at different durations of the input. Our simulations showed that the LSM-based framework achieve outstanding results in comparison with other works using different emotion prediction scenarios with cross validation.