A spiking self-organizing map combining STDP, oscillations, and continuous learning

Spiking neural networks on FPGA: A survey of methodologies and recent advancements

The mimicry of the biological brain's structure in information processing enables spiking neural networks (SNNs) to exhibit significantly reduced power consumption compared to conventional systems. Consequently, these networks have garnered heightened attention and spurred extensive research endeavors in recent years, proposing various structures to achieve low power consumption, high speed, and improved recognition ability. However, researchers are still in the early stages of developing more efficient neural networks that more closely resemble the biological brain. This development and research require suitable hardware for execution with appropriate capabilities, and field-programmable gate array (FPGA) serves as a highly qualified candidate compared to existing hardware such as central processing unit (CPU) and graphics processing unit (GPU). FPGA, with parallel processing capabilities similar to the brain, lower latency and power consumption, and higher throughput, is highly eligible hardware for assisting in the development of spiking neural networks. In this review, an attempt has been made to facilitate researchers' path to further develop this field by collecting and examining recent works and the challenges that hinder the implementation of these networks on FPGA.

A SOM−RBFnn-Based Calibration Algorithm of Modeled Significant Wave Height for Nearshore Areas

In this paper, a calibration algorithm for forecasting the significant wave height (SWH) in nearshore areas is proposed, based on artificial neural networks. The algorithm has two features: first, it is based on SOM−BRFnn (self−organizing map–radial basis function neural network) to better reflect the clustering characteristics of the input parameters regarding wind and wave. In addition, the high-frequency variation part and the low-frequency variation part of SWH are separated by a threshold of 24 h to better describe the diurnal variation of SWH under the influence of tidal current. The algorithm is applied to the nearshore region of Nan-ao Island in the northeastern South China Sea. The results show that the algorithm can effectively correct the modeling results of nearshore SWH. Compared with the original outputs of the ERA5 model, the correlation coefficient is increased from 0.472 to 0.774, the root mean square error is reduced from 0.252 m to 0.103 m, and the mean relative error is reduced from 41% to 17.6%, respectively. Further analysis indicates that the frequency division is crucial in realizing the correction of the high-frequency variation of SWH. The results have reference significance for the application of wave numerical models in coastal areas.

A Bio-Inspired Mechanism for Learning Robot Motion From Mirrored Human Demonstrations

Different learning modes and mechanisms allow faster and better acquisition of skills as widely studied in humans and many animals. Specific neurons, called mirror neurons, are activated in the same way whether an action is performed or simply observed. This suggests that observing others performing movements allows to reinforce our motor abilities. This implies the presence of a biological mechanism that allows creating models of others' movements and linking them to the self-model for achieving mirroring. Inspired by such ability, we propose to build a map of movements executed by a teaching agent and mirror the agent's state to the robot's configuration space. Hence, in this study, a neural network is proposed to integrate a motor cortex-like differential map transforming motor plans from task-space to joint-space motor commands and a static map correlating joint-spaces of the robot and a teaching agent. The differential map is developed based on spiking neural networks while the static map is built as a self-organizing map. The developed neural network allows the robot to mirror the actions performed by a human teaching agent to its own joint-space and the reaching skill is refined by the complementary examples provided. Hence, experiments are conducted to quantify the improvement achieved thanks to the proposed learning approach and control scheme.

Biological constraints on neural network models of cognitive function

Neural network models are potential tools for improving our understanding of complex brain functions. To address this goal, these models need to be neurobiologically realistic. However, although neural networks have advanced dramatically in recent years and even achieve human-like performance on complex perceptual and cognitive tasks, their similarity to aspects of brain anatomy and physiology is imperfect. Here, we discuss different types of neural models, including localist, auto-associative, hetero-associative, deep and whole-brain networks, and identify aspects under which their biological plausibility can be improved. These aspects range from the choice of model neurons and of mechanisms of synaptic plasticity and learning to implementation of inhibition and control, along with neuroanatomical properties including areal structure and local and long-range connectivity. We highlight recent advances in developing biologically grounded cognitive theories and in mechanistically explaining, on the basis of these brain-constrained neural models, hitherto unaddressed issues regarding the nature, localization and ontogenetic and phylogenetic development of higher brain functions. In closing, we point to possible future clinical applications of brain-constrained modelling.

Pulsewidth Modulation-Based Algorithm for Spike Phase Encoding and Decoding of Time-Dependent Analog Data

This article proposes a new spike encoding and decoding algorithm for analog data. The algorithm uses the pulsewidth modulation principles to achieve a high reconstruction accuracy of the signal, along with a high level of data compression. Two benchmark data sets are used to illustrate the method: stock index time series and human voice data. Applications of the method for spiking neural network (SNN) modeling and neuromorphic implementations are discussed. The proposed method would allow the development of new applications of SNNs as regression techniques for predictive time-series modeling.

Deep Spiking Neural Network for Video-Based Disguise Face Recognition Based on Dynamic Facial Movements

With the increasing popularity of social media and smart devices, the face as one of the key biometrics becomes vital for person identification. Among those face recognition algorithms, video-based face recognition methods could make use of both temporal and spatial information just as humans do to achieve better classification performance. However, they cannot identify individuals when certain key facial areas, such as eyes or nose, are disguised by heavy makeup or rubber/digital masks. To this end, we propose a novel deep spiking neural network architecture in this paper. It takes dynamic facial movements, the facial muscle changes induced by speaking or other activities, as the sole input. An event-driven continuous spike-timing-dependent plasticity learning rule with adaptive thresholding is applied to train the synaptic weights. The experiments on our proposed video-based disguise face database (MakeFace DB) demonstrate that the proposed learning method performs very well, i.e., it achieves from 95% to 100% correct classification rates under various realistic experimental scenarios.

Event-Driven Continuous STDP Learning With Deep Structure for Visual Pattern Recognition

Human beings can achieve reliable and fast visual pattern recognition with limited time and learning samples. Underlying this capability, ventral stream plays an important role in object representation and form recognition. Modeling the ventral steam may shed light on further understanding the visual brain in humans and building artificial vision systems for pattern recognition. The current methods to model the mechanism of ventral stream are far from exhibiting fast, continuous, and event-driven learning like the human brain. To create a visual system similar to ventral stream in human with fast learning capability, in this paper, we propose a new spiking neural system with an event-driven continuous spike timing dependent plasticity (STDP) learning method using specific spiking timing sequences. Two novel continuous input mechanisms have been used to obtain the continuous input spiking pattern sequence. With the event-driven STDP learning rule, the proposed learning procedure will be activated if the neuron receive one pre- or post-synaptic spike event. The experimental results on MNIST database show that the proposed method outperforms all other methods in fast learning scenarios and most of the current models in exhaustive learning experiments.

Fine-Grained Image Classification Using Modified DCNNs Trained by Cascaded Softmax and Generalized Large-Margin Losses

We develop a fine-grained image classifier using a general deep convolutional neural network (DCNN). We improve the fine-grained image classification accuracy of a DCNN model from the following two aspects. First, to better model the h -level hierarchical label structure of the fine-grained image classes contained in the given training data set, we introduce h fully connected (fc) layers to replace the top fc layer of a given DCNN model and train them with the cascaded softmax loss. Second, we propose a novel loss function, namely, generalized large-margin (GLM) loss, to make the given DCNN model explicitly explore the hierarchical label structure and the similarity regularities of the fine-grained image classes. The GLM loss explicitly not only reduces between-class similarity and within-class variance of the learned features by DCNN models but also makes the subclasses belonging to the same coarse class be more similar to each other than those belonging to different coarse classes in the feature space. Moreover, the proposed fine-grained image classification framework is independent and can be applied to any DCNN structures. Comprehensive experimental evaluations of several general DCNN models (AlexNet, GoogLeNet, and VGG) using three benchmark data sets (Stanford car, fine-grained visual classification-aircraft, and CUB-200-2011) for the fine-grained image classification task demonstrate the effectiveness of our method.

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.

Implementing Signature Neural Networks with Spiking Neurons

Spiking Neural Networks constitute the most promising approach to develop realistic Artificial Neural Networks (ANNs). Unlike traditional firing rate-based paradigms, information coding in spiking models is based on the precise timing of individual spikes. It has been demonstrated that spiking ANNs can be successfully and efficiently applied to multiple realistic problems solvable with traditional strategies (e.g., data classification or pattern recognition). In recent years, major breakthroughs in neuroscience research have discovered new relevant computational principles in different living neural systems. Could ANNs benefit from some of these recent findings providing novel elements of inspiration? This is an intriguing question for the research community and the development of spiking ANNs including novel bio-inspired information coding and processing strategies is gaining attention. From this perspective, in this work, we adapt the core concepts of the recently proposed Signature Neural Network paradigm—i.e., neural signatures to identify each unit in the network, local information contextualization during the processing, and multicoding strategies for information propagation regarding the origin and the content of the data—to be employed in a spiking neural network. To the best of our knowledge, none of these mechanisms have been used yet in the context of ANNs of spiking neurons. This paper provides a proof-of-concept for their applicability in such networks. Computer simulations show that a simple network model like the discussed here exhibits complex self-organizing properties. The combination of multiple simultaneous encoding schemes allows the network to generate coexisting spatio-temporal patterns of activity encoding information in different spatio-temporal spaces. As a function of the network and/or intra-unit parameters shaping the corresponding encoding modality, different forms of competition among the evoked patterns can emerge even in the absence of inhibitory connections. These parameters also modulate the memory capabilities of the network. The dynamical modes observed in the different informational dimensions in a given moment are independent and they only depend on the parameters shaping the information processing in this dimension. In view of these results, we argue that plasticity mechanisms inside individual cells and multicoding strategies can provide additional computational properties to spiking neural networks, which could enhance their capacity and performance in a wide variety of real-world tasks.

No Neuron Left Behind: A genetic approach to higher precision topological mapping of self-organizing maps

Self-organizing maps are extremely useful in the field of pattern recognition. They become less useful, however, when neurons fail to activate during training. This phenomenon occurs when neurons are initialized in areas of non-input and are far enough away from the input data to never move toward the input. These neurons effectively misrepresent the data set. This results in, among other things, patterns becoming unrecognizable.We introduce an algorithm called No Neuron Left Behind to solve this problem.We show that our algorithm produces a more accurate topological representation of the input space.We also show that no neuron clusters form in areas of noninput and that mapping quality of the SOM increases drastically when our algorithm is implemented. Finally, the running time of NNLB is better or comparable to classic SOM without it.