Neural modeling of episodic memory: encoding, retrieval, and forgetting

Spiking neural network-based computational modeling of episodic memory

In this research article, a spiking neural network-based simulation of the hippocampus is performed to model the functionalities of episodic memory. The purpose of the simulation is to find a computational model through the biological architecture of the hippocampus and correct values for their architectural biological parameters to support the episodic memory functionalities. The episodic store of the model is represented by the collection of events, where each event is further subdivided into coactive activities of experience. The model has tried to mimic the three functionalities of episodic memory, which are pattern separation, pattern association, and their recallings. In pattern separation model used the dentate biological connectivity to generate almost different output patterns corresponding to similar input patterns to reduce interference between two similar memory traces so that ambiguity can be reduced during recalling. In pattern association, an STDP based event encoding and forgetting mechanism are used to mimic the encoding function of the CA3 region in which the coactive activities get associated with each other. A decoder is proposed based on CA1, which can answer the stored event related queries. Along with these functionalities model also supports recalling and encoding based forgetting. Experimental work is performed on the model for the given set of events to check for the pattern separation efficiency, pattern completion efficiency and to check the capability of decoding the answer. An empirical analysis of the results is done and compared with the SMRITI model of episodic memory.

Vision-Based Topological Mapping and Navigation With Self-Organizing Neural Networks

Spatial mapping and navigation are critical cognitive functions of autonomous agents, enabling one to learn an internal representation of an environment and move through space with real-time sensory inputs, such as visual observations. Existing models for vision-based mapping and navigation, however, suffer from memory requirements that increase linearly with exploration duration and indirect path following behaviors. This article presents e -TM, a self-organizing neural network-based framework for incremental topological mapping and navigation. e -TM models the exploration trajectories explicitly as episodic memory, wherein salient landmarks are sequentially extracted as "events" from streaming observations. A memory consolidation procedure then performs a playback mechanism and transfers the embedded knowledge of the environmental layout into spatial memory, encoding topological relations between landmarks. Fusion adaptive resonance theory (ART) networks, as the building block of the two memory modules, can generalize multiple input patterns into memory templates and, therefore, provide a compact spatial representation and support the discovery of novel shortcuts through inferences. For navigation, e -TM applies a transfer learning paradigm to integrate human demonstrations into a pretrained locomotion network for smoother movements. Experimental results based on VizDoom, a simulated 3-D environment, have shown that, compared to semiparametric topological memory (SPTM), a state-of-the-art model, e -TM reduces the time costs of navigation significantly while learning much sparser topological graphs.

SR-EM: Episodic Memory Aware of Semantic Relations Based on Hierarchical Clustering Resonance Network

An intelligent robot requires episodic memory that can retrieve a sequence of events for a service task learned from past experiences to provide a proper service to a user. Various episodic memories, which can learn new tasks incrementally without forgetting the tasks learned previously, have been designed based on adaptive resonance theory (ART) networks. The conventional ART-based episodic memories, however, do not have the adaptability to the changing environments. They cannot utilize the retrieved task episode adaptively in the working environment. Moreover, if a user wants to receive multiple services of the same kind in a given situation, the user should repeatedly command multiple times. To tackle these limitations, in this article, a novel hierarchical clustering resonance network (HCRN) is proposed, which has a high clustering performance on multimodal data and can compute the semantic relations between learned clusters. Using HCRN, a semantic relation-aware episodic memory (SR-EM) is designed, which can adapt the retrieved task episode to the current working environment to carry out the task intelligently. Experimental simulations demonstrate that HCRN outperforms the conventional ART in terms of clustering performance on multimodal data. Besides, the effectiveness of the proposed SR-EM is verified through robot simulations for two scenarios.

Who are the 'silent spreaders'?: contact tracing in spatio-temporal memory models

The COVID-19 epidemic has swept the world for over two years. However, a large number of infectious asymptomatic COVID-19 cases (ACCs) are still making the breaking up of the transmission chains very difficult. Efforts by epidemiological researchers in many countries have thrown light on the clinical features of ACCs, but there is still a lack of practical approaches to detect ACCs so as to help contain the pandemic. To address the issue of ACCs, this paper presents a neural network model called Spatio-Temporal Episodic Memory for COVID-19 (STEM-COVID) to identify ACCs from contact tracing data. Based on the fusion Adaptive Resonance Theory (ART), the model encodes a collective spatio-temporal episodic memory of individuals and incorporates an effective mechanism of parallel searches for ACCs. Specifically, the episodic traces of the identified positive cases are used to map out the episodic traces of suspected ACCs using a weighted evidence pooling method. To evaluate the efficacy of STEM-COVID, a realistic agent-based simulation model for COVID-19 spreading is implemented based on the recent epidemiological findings on ACCs. The experiments based on rigorous simulation scenarios, manifesting the current situation of COVID-19 spread, show that the STEM-COVID model with weighted evidence pooling has a higher level of accuracy and efficiency for identifying ACCs when compared with several baselines. Moreover, the model displays strong robustness against noisy data and different ACC proportions, which partially reflects the effect of breakthrough infections after vaccination on the virus transmission.

Virtual reality experiences promote autobiographical retrieval mechanisms: Electrophysiological correlates of laboratory and virtual experiences

Recent advancements in memory research indicate that virtual reality (VR) experiences are more vividly memorized as compared to conventional laboratory events. In contrast to the latter, VR experiences are highly immersive, simulating the multimodality, vividness and inclusiveness of real-life experiences. Therefore, VR might enable researchers to identify memory processes underlying events which participants have actually experienced, in contrast to conventional on-screen experiences. To differentiate the electrophysiological correlates of memory processes underlying VR experiences as compared to conventional laboratory experiences, participants watched videos either in a PC condition or in a VR condition, followed by an unannounced recognition memory test. As hypothesized, we replicated the well-established theta old/new effect for the PC condition, but remarkably, this effect was absent in the VR condition. Additionally, the latter was accompanied by significantly lower alpha activity as compared to the PC condition. As increases in theta-band responses are related to top-down control on, and memory load during retrieval, the observed theta responses might rather relate to retrieval effort than to retrieval success per se. Congruently, higher alpha activity measured over occipital sensor areas in the PC condition reflect visually guided search processes within episodic memory. The VR condition comes in with lower alpha activity, reflecting immediate and effortless memory access. Hence, our findings indicate that the retrieval of VR experiences promotes autobiographical  retrieval mechanisms, whereas recalling conventional laboratory events comes in with higher effort, which might not reflect the mechanisms of everyday memory.

Lifelogging as a rehabilitation tool in patients with amnesia: A narrative literature review on the effect of lifelogging on memory loss

Visual lifelogging is the procedure that enables individuals to visually record daily life activities by means of small wearable cameras, which can be worn around the neck or on the clothing. Lifelogging devices automatically take pictures or videos after pre-set time intervals or after dynamic input changes. Although some studies have shown effectivity of reviewing lifelogging images in brain-damaged individuals with forms of amnesia as a rehabilitation tool, systematic endeavours to overview this literature is yet missing. The aim of this narrative literature review was to review all the available case-studies, experimental studies and group studies in brain-damaged individuals applying lifelogging devices in a clinical context. The included studies showed efficacy for both subjective and objective measures of memory. In mild to severe amnesia, reviewing images recorded by the lifelogging device was beneficial to subjective and objective measures of memory. Lifelogging is demonstrated to have a great potential in helping people who are suffering from memory loss. It can offer an excellent alternative to currently more frequently used memory rehabilitation techniques and can be applied more in clinical settings.

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.

A Stabilized Feedback Episodic Memory (SF-EM) and Home Service Provision Framework for Robot and IoT Collaboration

The automated home referred to as Smart Home is expected to offer fully customized services to its residents, reducing the amount of home labor, thus improving human beings' welfare. Service robots and Internet of Things (IoT) play the key roles in the development of Smart Home. The service provision with these two main components in a Smart Home environment requires: 1) learning and reasoning algorithms and 2) the integration of robot and IoT systems. Conventional computational intelligence-based learning and reasoning algorithms do not successfully manage dynamic changes in the Smart Home data, and the simple integrations fail to fully draw the synergies from the collaboration of the two systems. To tackle these limitations, we propose: 1) a stabilized memory network with a feedback mechanism which can learn user behaviors in an incremental manner and 2) a robot-IoT service provision framework for a Smart Home which utilizes the proposed memory architecture as a learning and reasoning module and exploits synergies between the robot and IoT systems. We conduct a set of comprehensive experiments under various conditions to verify the performance of the proposed memory architecture and the service provision framework and analyze the experiment results.

Immune-Endocrine System Inspired Hierarchical Coevolutionary Multiobjective Optimization Algorithm for IoT Service

The intelligent devices in Internet of Things (IoT) not only provide services but also consider how to allocate heterogeneous resources and reduce resource consumption and service time as far as possible. This issue becomes crucial in the case of large-scale IoT environments. In order for the IoT service system to respond to multiple requests simultaneously and provide Pareto optimal decisions, we propose an immune-endocrine system inspired hierarchical coevolutionary multiobjective optimization algorithm (IE-HCMOA) in this paper. In IE-HCMOA, a multiobjective immune algorithm based on global ranking with vaccine is designed to choose superior antibodies. Meanwhile, we adopt clustering in top population to make the operations more directional and purposeful and realize self-adaptive searching. And we use the human forgetting memory mechanism to design two-level memory storage for the choice problem of solutions to achieve promising performance. In order to validate the practicability and effectiveness of IE-HCMOA, we apply it to the field of agricultural IoT service. The simulation results demonstrate that the proposed algorithm can obtain the best Pareto, the strongest exploration ability, and excellent performance than nondominated neighbor immune algorithms and NSGA-II.

Self-organizing neural networks for universal learning and multimodal memory encoding

Learning and memory are two intertwined cognitive functions of the human brain. This paper shows how a family of biologically-inspired self-organizing neural networks, known as fusion Adaptive Resonance Theory (fusion ART), may provide a viable approach to realizing the learning and memory functions. Fusion ART extends the single-channel Adaptive Resonance Theory (ART) model to learn multimodal pattern associative mappings. As a natural extension of ART, various forms of fusion ART have been developed for a myriad of learning paradigms, ranging from unsupervised learning to supervised learning, semi-supervised learning, multimodal learning, reinforcement learning, and sequence learning. In addition, fusion ART models may be used for representing various types of memories, notably episodic memory, semantic memory and procedural memory. In accordance with the notion of embodied intelligence, such neural models thus provide a computational account of how an autonomous agent may learn and adapt in a real-world environment. The efficacy of fusion ART in learning and memory shall be discussed through various examples and illustrative case studies.

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.

Developmental Resonance Network

Adaptive resonance theory (ART) networks deal with normalized input data only, which means that they need the normalization process for the raw input data, under the assumption that the upper and lower bounds of the input data are known in advance. Without such an assumption, ART networks cannot be utilized. To solve this problem and improve the learning performance, inspired by the ART networks, we propose a developmental resonance network (DRN) by employing new techniques of a global weight and node connection and grouping processes. The proposed DRN learns the global weight converging to the unknown range of the input data and properly clusters by grouping similar nodes into one. These techniques enable DRN to learn the raw input data without the normalization process while retaining the stability, plasticity, and memory usage efficiency without node proliferation. Simulation results verify that our DRN, applied to the unsupervised clustering problem, can cluster raw data properly without a prior normalization process.

A Highly Effective and Robust Membrane Potential-Driven Supervised Learning Method for Spiking Neurons

Spiking neurons are becoming increasingly popular owing to their biological plausibility and promising computational properties. Unlike traditional rate-based neural models, spiking neurons encode information in the temporal patterns of the transmitted spike trains, which makes them more suitable for processing spatiotemporal information. One of the fundamental computations of spiking neurons is to transform streams of input spike trains into precisely timed firing activity. However, the existing learning methods, used to realize such computation, often result in relatively low accuracy performance and poor robustness to noise. In order to address these limitations, we propose a novel highly effective and robust membrane potential-driven supervised learning (MemPo-Learn) method, which enables the trained neurons to generate desired spike trains with higher precision, higher efficiency, and better noise robustness than the current state-of-the-art spiking neuron learning methods. While the traditional spike-driven learning methods use an error function based on the difference between the actual and desired output spike trains, the proposed MemPo-Learn method employs an error function based on the difference between the output neuron membrane potential and its firing threshold. The efficiency of the proposed learning method is further improved through the introduction of an adaptive strategy, called skip scan training strategy, that selectively identifies the time steps when to apply weight adjustment. The proposed strategy enables the MemPo-Learn method to effectively and efficiently learn the desired output spike train even when much smaller time steps are used. In addition, the learning rule of MemPo-Learn is improved further to help mitigate the impact of the input noise on the timing accuracy and reliability of the neuron firing dynamics. The proposed learning method is thoroughly evaluated on synthetic data and is further demonstrated on real-world classification tasks. Experimental results show that the proposed method can achieve high learning accuracy with a significant improvement in learning time and better robustness to different types of noise.

User Preference-Based Dual-Memory Neural Model With Memory Consolidation Approach

Memory modeling has been a popular topic of research for improving the performance of autonomous agents in cognition related problems. Apart from learning distinct experiences correctly, significant or recurring experiences are expected to be learned better and be retrieved easier. In order to achieve this objective, this paper proposes a user preference-based dual-memory adaptive resonance theory network model, which makes use of a user preference to encode memories with various strengths and to learn and forget at various rates. Over a period of time, memories undergo a consolidation-like process at a rate proportional to the user preference at the time of encoding and the frequency of recall of a particular memory. Consolidated memories are easier to recall and are more stable. This dual-memory neural model generates distinct episodic memories and a flexible semantic-like memory component. This leads to an enhanced retrieval mechanism of experiences through two routes. The simulation results are presented to evaluate the proposed memory model based on various kinds of cues over a number of trials. The experimental results on Mybot are also presented. The results verify that not only are distinct experiences learned correctly but also that experiences associated with higher user preference and recall frequency are consolidated earlier. Thus, these experiences are recalled more easily relative to the unconsolidated experiences.

Remembering a Conversation – A Conversational Memory Architecture for Embodied Conversational Agents

This paper addresses the role of conversational memory in Embodied Conversational Agents (ECAs). It describes an investigation into developing such a memory architecture and integrating it into an ECA. ECAs are virtual agents whose purpose is to engage in conversations with human users, typically through natural language speech. While several works in the literature seek to produce viable ECA dialog architectures, only a few authors have addressed the episodic memory architectures in conversational agents and their role in enhancing their intelligence. In this work, we propose, implement, and test a unified episodic memory architecture for ECAs. We describe a process that determines the prevalent contexts in the conversations obtained from the interactions. The process presented demonstrates the use of multiple techniques to extract and store relevant snippets from long conversations, most of whose contents are unremarkable and need not be remembered. The mechanisms used to store, retrieve, and recall episodes from previous conversations are presented and discussed. Finally, we test our episodic memory architecture to assess its effectiveness. The results indicate moderate success in some aspects of the memory-enhanced ECAs, as well as some work still to be done in other aspects.

Rapid feedforward computation by temporal encoding and learning with spiking neurons

Primates perform remarkably well in cognitive tasks such as pattern recognition. Motivated by recent findings in biological systems, a unified and consistent feedforward system network with a proper encoding scheme and supervised temporal rules is built for solving the pattern recognition task. The temporal rules used for processing precise spiking patterns have recently emerged as ways of emulating the brain's computation from its anatomy and physiology. Most of these rules could be used for recognizing different spatiotemporal patterns. However, there arises the question of whether these temporal rules could be used to recognize real-world stimuli such as images. Furthermore, how the information is represented in the brain still remains unclear. To tackle these problems, a proper encoding method and a unified computational model with consistent and efficient learning rule are proposed. Through encoding, external stimuli are converted into sparse representations, which also have properties of invariance. These temporal patterns are then learned through biologically derived algorithms in the learning layer, followed by the final decision presented through the readout layer. The performance of the model with images of digits from the MNIST database is presented. The results show that the proposed model is capable of recognizing images correctly with a performance comparable to that of current benchmark algorithms. The results also suggest a plausibility proof for a class of feedforward models of rapid and robust recognition in the brain.