Spiking Neurons Research Articles

Analog Sequential Hippocampal Memory Model for Trajectory Learning and Recalling: A Robustness Analysis Overview

The rapid expansion of information systems in all areas of society demands more powerful, efficient, and low‐energy consumption computing systems. Neuromorphic engineering has emerged as a solution that attempts to mimic the brain to incorporate its capabilities to solve complex problems in a computationally and energy‐efficient way in real time. Within neuromorphic computing, building systems to efficiently store the information is still a challenge. Among all the brain regions, the hippocampus stands out as a short‐term memory capable of learning and recalling large amounts of information quickly and efficiently. Herein, a spike‐based bio‐inspired hippocampus sequential memory model is proposed that makes use of the benefits of analog computing and spiking neural networks (SNNs): noise robustness, improved real‐time operation, and energy efficiency. This model is applied to robotic navigation to learn and recall trajectories that lead to a goal position within a known grid environment. The model is implemented on the special‐purpose SNNs mixed‐signal DYNAP‐SE hardware platform. Through extensive experimentation together with an extensive analysis of the model's behavior in the presence of external noise sources, its correct functioning is demonstrated, proving the robustness and consistency of the proposed neuromorphic sequential memory system.

Programmable Optical Synaptic Linking of Neuromorphic Photonic-Electronic RTD Spiking Circuits.

Interconnectivity between functional building blocks (such as neurons and synapses) represents a fundamental functionality for realizing neuromorphic systems. However, in the domain of neuromorphic photonics, synaptic interlinking and cascadability of spiking optical artificial neurons remains challenging and mostly unexplored in experiments. In this work, we report an optical synaptic link between optoelectronic spiking artificial neurons based upon resonant tunneling diodes (RTDs) that allows for cascadable spike propagation. First, deterministic spiking is triggered using multimodal (electrical and optical) inputs in RTD-based spiking artificial neurons, which are optoelectronic (OE) circuits incorporating either micron-scale RTDs or photosensitive nanopillar-based RTDs. Second, feedforward linking with dynamical weighting of optical spiking signals between pre- and postsynaptic RTD artificial neurons is demonstrated, including cascaded spike activation. By dynamically weighting the amplitude of optical spikes, it is shown how the cascaded spike activation probability in the postsynaptic RTD node directly follows the amplitude of the weighted optical spikes. This work therefore provides the first experimental demonstration of programmable synaptic optical link and spike cascading between multiple fast and efficient RTD OE spiking artificial neurons, therefore providing a key functionality for photonic-electronic spiking neural networks and light-enabled neuromorphic hardware.

A two-stage strategy for brain-inspired unsupervised learning in spiking neural networks

Spiking Neural Networks (SNNs) are emerging as a promising model in the field of neuromorphic computing, offering possibilities for efficient bio-inspired computing. Unsupervised learning in SNNs plays a crucial role in exploring neural network dynamics and achieving efficient artificial intelligence systems. However, current unsupervised learning in SNNs mostly relies on single-stage learning strategies, which limits the possibility of combining diverse learning mechanisms and network structures, resulting in networks that lack flexibility and adaptability for low-power task processing. Inspired by the multi-stage and multi-strategy learning in the human brain, this paper proposes a two-stage learning strategy from coarse to fine to enhance the efficiency of unsupervised learning in SNNs. To quickly extract structural features from spike data in the first stage, we propose the Spiking-SOM algorithm, which effectively learns patterns in spike data and achieves clustering effects. Additionally, we integrate Rate encoding and Temporal encoding through a visual attention mechanism, where this hybrid encoding helps meet the need for rapid information processing in the first stage, while also aiding in detailed feature representation in the second stage. Compared to the traditional single-stage learning framework, this work maintains high accuracy in unsupervised classification while significantly reducing computational costs and speeding up training. This exploration offers a new direction for future learning frameworks in SNNs, helping to further improve the energy efficiency of the network.

Spiking Neural Networks for event-based action recognition: A new task to understand their advantage

Spiking Neural Networks (SNN) are characterised by their unique temporal dynamics, but the properties and advantages of such computations are still not well understood. In order to provide answers, in this work we demonstrate how Spiking neurons can enable temporal feature extraction in feed-forward neural networks without the need for recurrent synapses, and how recurrent SNNs can achieve comparable results to LSTM with a smaller number of parameters. This shows how their bio-inspired computing principles can be successfully exploited beyond energy efficiency gains and evidences their differences with respect to conventional artificial neural networks. These results are obtained through a new task, DVS-Gesture-Chain (DVS-GC), which allows, for the first time, to evaluate the perception of temporal dependencies in a real event-based action recognition dataset. Our study proves how the widely used DVS Gesture benchmark can be solved by networks without temporal feature extraction when its events are accumulated in frames, unlike the new DVS-GC which demands an understanding of the order in which events happen. Furthermore, this setup allowed us to reveal the role of the leakage rate in spiking neurons for temporal processing tasks and demonstrated the benefits of ”hard reset” mechanisms. Additionally, we also show how time-dependent weights and normalisation can lead to understanding order by means of temporal attention. Code for the DVS-GC task is available.

Pattern recognition using spiking antiferromagnetic neurons

Spintronic devices offer a promising avenue for the development of nanoscale, energy-efficient artificial neurons for neuromorphic computing. It has previously been shown that with antiferromagnetic (AFM) oscillators, ultra-fast spiking artificial neurons can be made that mimic many unique features of biological neurons. In this work, we train an artificial neural network of AFM neurons to perform pattern recognition. A simple machine learning algorithm called spike pattern association neuron (SPAN), which relies on the temporal position of neuron spikes, is used during training. In under a microsecond of physical time, the AFM neural network is trained to recognize symbols composed from a grid by producing a spike within a specified time window. We further achieve multi-symbol recognition with the addition of an output layer to suppress undesirable spikes. Through the utilization of AFM neurons and the SPAN algorithm, we create a neural network capable of high-accuracy recognition with overall power consumption on the order of picojoules.

Impact of the La2NiO4+δ Oxygen Content on the Synaptic Properties of the TiN/La2NiO4+δ/Pt Memristive Devices

AbstractThe rapid development of brain‐inspired computing requires new artificial components and architectures for its hardware implementation. In this regard, memristive devices emerged as potential candidates for artificial synapses because of their ability to emulate the plasticity of the biological synapses. In this work, the synaptic behavior of the TiN/La2NiO4+δ/Pt memristive devices based on thermally annealed La2NiO4+δ films is thoroughly investigated. Using electron energy loss spectroscopy (EELS), it is shown that post‐deposition annealing using inert (Ar) or oxidizing (O2) atmospheres affects the interstitial oxygen content (δ) in the La2NiO4+δ films. Electrical characterization shows that both devices exhibit long‐term potentiation/depression (LTP/LTD) and spike‐timing‐dependent plasticity (STDP). At the same time, the Ar annealed TiN/La2NiO4+δ/Pt device demonstrates filamentary‐like behavior, fast switching, and low energy consumption. On the other hand, the O2 annealed TiN/La2NiO4+δ/Pt devices are forming‐free, exhibiting interfacial‐like resistive switching with slower kinetics. Finally, the simulation tools show that spiking neural network (SNN) architectures with weight updates based on the experimental data achieve high inference accuracy in the digit recognition task, which proves the potential of TiN/La2NiO4+δ/Pt devices for artificial synapse applications.

Graph spiking neural network for advanced urban flood risk assessment

Urban flooding significantly impacts city planning and resident safety. Traditional flood risk models, divided into physical and data-driven types, face challenges like data requirements and limited scalability. To overcome these, this study developed a model combining graph convolutional network (GCN) and spiking neural network (SNN), enabling the extraction of both spatial and temporal features from diverse data sources. We built a comprehensive flood risk dataset by integrating social media reports with weather and geographical data from six Chinese cities. The proposed Graph SNN model demonstrated superior performance compared to GCN and LSTM models, achieving high accuracy (85.3%), precision (0.811), recall (0.832), and F1 score (0.821). It also exhibited higher energy efficiency, making it scalable for real-time flood prediction in various urban environments. This research advances flood risk assessment by efficiently processing heterogeneous data while reducing energy consumption, offering a sustainable solution for urban flood management.

Exploring neural oscillations during speech perception via surrogate gradient spiking neural networks.

Understanding cognitive processes in the brain demands sophisticated models capable of replicating neural dynamics at large scales. We present a physiologically inspired speech recognition architecture, compatible and scalable with deep learning frameworks, and demonstrate that end-to-end gradient descent training leads to the emergence of neural oscillations in the central spiking neural network. Significant cross-frequency couplings, indicative of these oscillations, are measured within and across network layers during speech processing, whereas no such interactions are observed when handling background noise inputs. Furthermore, our findings highlight the crucial inhibitory role of feedback mechanisms, such as spike frequency adaptation and recurrent connections, in regulating and synchronizing neural activity to improve recognition performance. Overall, on top of developing our understanding of synchronization phenomena notably observed in the human auditory pathway, our architecture exhibits dynamic and efficient information processing, with relevance to neuromorphic technology.

Supervised learning of spatial features with STDP and homeostasis using Spiking Neural Networks on SpiNNaker

Artificial Neural Networks (ANN) have gained significant popularity thanks to their ability to learn using the well-known backpropagation algorithm. Conversely, Spiking Neural Networks (SNNs), despite having broader capabilities than ANNs, have always posed challenges in the training phase. This paper shows a new method to perform supervised learning on SNNs, using Spike Timing Dependent Plasticity (STDP) and homeostasis, aiming at training the network to identify spatial patterns. Spatial patterns refer to spike patterns without a time component, where all spike events occur simultaneously. The method is tested using the SpiNNaker digital architecture. A SNN is trained to recognise one or multiple patterns and performance metrics are extracted to measure the performance of the network. Some considerations are drawn from the results showing that, in the case of a single trained pattern, the network behaves as the ideal detector, with 100% accuracy in detecting the trained pattern. However, as the number of trained patterns on a single network increases, the accuracy of identification is linked to the similarities between these patterns. This method of training an SNN to detect spatial patterns may be applied to pattern recognition in static images or traffic analysis in computer networks, where each network packet represents a spatial pattern. It will be stipulated that the homeostatic factor may enable the network to detect patterns with some degree of similarity, rather than only perfectly matching patterns. The principles outlined in this article serve as the fundamental building blocks for more complex systems that utilise both spatial and temporal patterns by converting specific features of input signals into spikes. One example of such a system is a computer network packet classifier, tasked with real-time identification of packet streams based on features within the packet content.

Statistical Inference for Networks of High-Dimensional Point Processes

Fueled in part by recent applications in neuroscience, the multivariate Hawkes process has become a popular tool for modeling the network of interactions among high-dimensional point process data. While evaluating the uncertainty of the network estimates is critical in scientific applications, existing methodological and theoretical work has primarily addressed estimation. To bridge this gap, we develop a new statistical inference procedure for high-dimensional Hawkes processes. The key ingredient for the inference procedure is a new concentration inequality on the first- and second-order statistics for integrated stochastic processes, which summarize the entire history of the process. Combining recent martingale central limit theorem with the new concentration inequality, we then characterize the convergence rate of the test statistics in a continuous time domain. Finally, to account for potential non-stationarity of the process in practice, we extend our statistical inference procedure to a flexible class of Hawkes processes with time-varying background intensities and unknown transition functions. The finite sample validity of the inferential tools is illustrated via extensive simulations and further applied to a neuron spike train dataset. Supplementary materials for this article are available online, including a standardized description of the materials available for reproducing the work.

Energy-aware bio-inspired spiking reinforcement learning system architecture for real-time autonomous edge applications.

Mobile, low-cost, and energy-aware operation of Artificial Intelligence (AI) computations in smart circuits and autonomous robots will play an important role in the next industrial leap in intelligent automation and assistive devices. Neuromorphic hardware with spiking neural network (SNN) architecture utilizes insights from biological phenomena to offer encouraging solutions. Previous studies have proposed reinforcement learning (RL) models for SNN responses in the rat hippocampus to an environment where rewards depend on the context. The scale of these models matches the scope and capacity of small embedded systems in the framework of Internet-of-Bodies (IoB), autonomous sensor nodes, and other edge applications. Addressing energy-efficient artificial learning problems in such systems enables smart micro-systems with edge intelligence. A novel bio-inspired RL system architecture is presented in this work, leading to significant energy consumption benefits without foregoing real-time autonomous processing and accuracy requirements of the context-dependent task. The hardware architecture successfully models features analogous to synaptic tagging, changes in the exploration schemes, synapse saturation, and spatially localized task-based activation observed in the brain. The design has been synthesized, simulated, and tested on Intel MAX10 Field-Programmable Gate Array (FPGA). The problem-based bio-inspired approach to SNN edge architectural design results in 25X reduction in average power compared to the state-of-the-art for a test with real-time context learning and 30 trials. Furthermore, 940x lower energy consumption is achieved due to improvement in the execution time.

Automatic fault detection and stability management using intelligent hybrid controller

Microgrid allows the integration of remote sources and other flexible loads to raise security concerns. Thus, it is necessary to detect the type of fault to maintain the system's stability. Existing fault detection systems include limitations such as high detection times, inability to process noisy data and discretization issues. To address these issues, a spiking neural network with a self-organizing map is used to produce precise synaptic weights for fault detection in the microgrid. A feature exploration-based spiking neural network can accurately classify faults such as line-to-ground (LG), line-to-line (LL), double line-to-ground (DLG), and three-phase ground (TLG). To mitigate the impact of the fault, a voltage deviation estimation-based control method is used, which employs a three-degree of freedom fractional order proportional integral resonant (3DOF-FOPIR) controller. In order to stabilize the system frequency, the controller sends a control signal to the multi-level inverter based on the measured voltage deviation and fault auxiliary value. This ensures reduced distortions at the output voltage, and thus, it maintains the stability of the microgrid. As a result, when compared to graph-based convolution networks, the proposed method has a higher accuracy of 99.8 % and a lower error in system stability of 55.47 %.

Learning long sequences in spiking neural networks

Spiking neural networks (SNNs) take inspiration from the brain to enable energy-efficient computations. Since the advent of Transformers, SNNs have struggled to compete with artificial networks on modern sequential tasks, as they inherit limitations from recurrent neural networks (RNNs), with the added challenge of training with non-differentiable binary spiking activations. However, a recent renewed interest in efficient alternatives to Transformers has given rise to state-of-the-art recurrent architectures named state space models (SSMs). This work systematically investigates, for the first time, the intersection of state-of-the-art SSMs with SNNs for long-range sequence modelling. Results suggest that SSM-based SNNs can outperform the Transformer on all tasks of a well-established long-range sequence modelling benchmark. It is also shown that SSM-based SNNs can outperform current state-of-the-art SNNs with fewer parameters on sequential image classification. Finally, a novel feature mixing layer is introduced, improving SNN accuracy while challenging assumptions about the role of binary activations in SNNs. This work paves the way for deploying powerful SSM-based architectures, such as large language models, to neuromorphic hardware for energy-efficient long-range sequence modelling.

A novel classification technique using a biologically plausible spiking neuron and noisy synapses

A novel classification technique using a biologically plausible spiking neuron and noisy synapses

Spiking representation learning for associative memories.

Networks of interconnected neurons communicating through spiking signals offer the bedrock of neural computations. Our brain's spiking neural networks have the computational capacity to achieve complex pattern recognition and cognitive functions effortlessly. However, solving real-world problems with artificial spiking neural networks (SNNs) has proved to be difficult for a variety of reasons. Crucially, scaling SNNs to large networks and processing large-scale real-world datasets have been challenging, especially when compared to their non-spiking deep learning counterparts. The critical operation that is needed of SNNs is the ability to learn distributed representations from data and use these representations for perceptual, cognitive and memory operations. In this work, we introduce a novel SNN that performs unsupervised representation learning and associative memory operations leveraging Hebbian synaptic and activity-dependent structural plasticity coupled with neuron-units modelled as Poisson spike generators with sparse firing (~1 Hz mean and ~100 Hz maximum firing rate). Crucially, the architecture of our model derives from the neocortical columnar organization and combines feedforward projections for learning hidden representations and recurrent projections for forming associative memories. We evaluated the model on properties relevant for attractor-based associative memories such as pattern completion, perceptual rivalry, distortion resistance, and prototype extraction.

Rapid distance estimation of odor sources by electronic nose with multi-sensor fusion based on spiking neural network

The inference of odor source locations holds great potential value in chemical leak detection, explosive searches and flammable substance detection. Sensor response and derivative changes are common indicators used to estimate source distance. However, most studies often rely on single-feature methods using a single sensor. In this study, a novel distance indicator based on a spiking neural network (SNN) that integrates multiple sensors is proposed. SNN was introduced for effective multi-sensor data fusion, which can provide accurate and rapid source distance estimation. The indicator's accuracy and quick detection capabilities were tested using a publicly available wind tunnel dataset and compared with single-sensor indicators. Additionally, an olfactory robot platform was constructed to test the method's real-time performance. Results demonstrate that this method effectively utilizes sensor arrays to estimate source distance, with an average root mean square error (RMSE) of less than 0.1 m across different wind speeds, outperforming single-sensor-based indicators. Additionally, the model exhibits good distance estimation performance within a relatively short detection time, with an average RMSE of 0.118 m. Practical testing on a mobile robot platform confirms the applicability of this distance indicator for real-time distance monitoring. In conclusion, the proposed distance indicator enables effective distance estimation for odor sources, providing a promising method for odor source localization and olfactory navigation.

SiGNN: A spike-induced graph neural network for dynamic graph representation learning

In the domain of dynamic graph representation learning (DGRL), capturing the temporal evolution within real-world networks is of paramount importance. Spiking Neural Networks (SNNs), renowned for their temporal dynamics and low-power characteristics, provide an efficient solution for temporal processing in DGRL tasks. However, due to the spike-based information encoding mechanism of SNNs, existing DGRL methods that employ SNNs face significant limitations in their representational capacity. To address this issue, we propose an innovative framework named Spike-induced Graph Neural Network (SiGNN) for learning enhanced spatiotemporal representations on dynamic graphs. Specifically, we achieve a harmonious integration of SNNs and GNNs through a novel Temporal Activation (TA) mechanism. This mechanism enables SiGNN to effectively harness the temporal dynamics of SNNs while circumventing the representational constraints imposed by the binary nature of spikes. Furthermore, leveraging the inherent adaptability of SNNs, SiGNN incorporates an in-depth analysis of evolutionary patterns within graphs across multiple time granularities, thereby facilitating the acquisition of multiscale temporal node representations. Extensive experiments on various real-world dynamic graph datasets demonstrate the superior performance of SiGNN in the node classification task. Our code is publicly available at https://github.com/CharliedoD/SiGNN.

Trainable Reference Spikes Improve Temporal Information Processing of SNNs With Supervised Learning.

Spiking neural networks (SNNs) are the next-generation neural networks composed of biologically plausible neurons that communicate through trains of spikes. By modifying the plastic parameters of SNNs, including weights and time delays, SNNs can be trained to perform various AI tasks, although in general not at the same level of performance as typical artificial neural networks (ANNs). One possible solution to improve the performance of SNNs is to consider plastic parameters other than just weights and time delays drawn from the inherent complexity of the neural system of the brain, which may help SNNs improve their information processing ability and achieve brainlike functions. Here, we propose reference spikes as a new type of plastic parameters in a supervised learning scheme in SNNs. A neuron receives reference spikes through synapses providing reference information independent of input to help during learning, whose number of spikes and timings are trainable by error backpropagation. Theoretically, reference spikes improve the temporal information processing of SNNs by modulating the integration of incoming spikes at a detailed level. Through comparative computational experiments, we demonstrate using supervised learning that reference spikes improve the memory capacity of SNNs to map input spike patterns to target output spike patterns and increase classification accuracy on the MNIST, Fashion-MNIST, and SHD data sets, where both input and target output are temporally encoded. Our results demonstrate that applying reference spikes improves the performance of SNNs by enhancing their temporal information processing ability.

Formation and retrieval of cell assemblies in a biologically realistic spiking neural network model of area CA3 in the mouse hippocampus

The hippocampal formation is critical for episodic memory, with area Cornu Ammonis 3 (CA3) a necessary substrate for auto-associative pattern completion. Recent theoretical and experimental evidence suggests that the formation and retrieval of cell assemblies enable these functions. Yet, how cell assemblies are formed and retrieved in a full-scale spiking neural network (SNN) of CA3 that incorporates the observed diversity of neurons and connections within this circuit is not well understood. Here, we demonstrate that a data-driven SNN model quantitatively reflecting the neuron type-specific population sizes, intrinsic electrophysiology, connectivity statistics, synaptic signaling, and long-term plasticity of the mouse CA3 is capable of robust auto-association and pattern completion via cell assemblies. Our results show that a broad range of assembly sizes could successfully and systematically retrieve patterns from heavily incomplete or corrupted cues after a limited number of presentations. Furthermore, performance was robust with respect to partial overlap of assemblies through shared cells, substantially enhancing memory capacity. These novel findings provide computational evidence that the specific biological properties of the CA3 circuit produce an effective neural substrate for associative learning in the mammalian brain.

A spiking neuron model of moral judgment in trolley dilemmas

People will make different moral judgments in similar moral dilemmas where one can act to sacrifice some number of lives to save several more. Research has shown that although people can reason that an action would save more lives, automatic processes can overwrite deliberate reasoning. Having participants imagine hypothetical moral dilemmas, researchers have discovered that factors such as action/omission, means/side-effect, and personal/impersonal can affect judgment. Joshua Greene suggests that these features do not affect people’s judgment because they are morally relevant but are instead a result of the myopic nature of the automatic moral process. Greene hypothesizes that there is some myopic module or domain-general process that attaches a negative emotional response to an action when one is contemplating violent actions. In the present research a model of this myopic automatic process is paired with an analytic system to replicate deontological and utilitarian responses to moral dilemmas. Our system, MERDJ, models this in simulated spiking neurons. The system takes in representations of specific moral dilemmas as inputs and outputs judgments of appropriate or inappropriate.