Performance Of Spiking Neural Networks Research Articles

Improving stability and performance of spiking neural networks through enhancing temporal consistency

Spiking neural networks have gained significant attention due to their brain-like information processing capabilities. The use of surrogate gradients has made it possible to train spiking neural networks with backpropagation, leading to impressive performance in various tasks. However, spiking neural networks trained with backpropagation typically approximate actual labels using the average output, often necessitating a larger simulation timestep to enhance the network’s performance. This delay constraint poses a challenge to the further advancement of spiking neural networks. Current training algorithms tend to overlook the differences in output distribution at various timesteps. Particularly for neuromorphic datasets, inputs at different timesteps can cause inconsistencies in output distribution, leading to a significant deviation from the optimal direction when combining optimization directions from different moments. To tackle this issue, we have designed a method to enhance the temporal consistency of outputs at different timesteps. We have conducted experiments on static datasets such as CIFAR10, CIFAR100, and ImageNet. The results demonstrate that our algorithm can achieve comparable performance to other optimal SNN algorithms. Notably, our algorithm has achieved state-of-the-art performance on neuromorphic datasets DVS-CIFAR10 and N-Caltech101, and can achieve superior performance in the test phase with timestep T=1.

Impact of Process Variation in Spin–Orbit Torque-Based Magnetic Tunnel Junctions on the Performance of Spiking Neural Networks

Impact of Process Variation in Spin–Orbit Torque-Based Magnetic Tunnel Junctions on the Performance of Spiking Neural Networks

Learnable axonal delay in spiking neural networks improves spoken word recognition.

Spiking neural networks (SNNs), which are composed of biologically plausible spiking neurons, and combined with bio-physically realistic auditory periphery models, offer a means to explore and understand human auditory processing-especially in tasks where precise timing is essential. However, because of the inherent temporal complexity in spike sequences, the performance of SNNs has remained less competitive compared to artificial neural networks (ANNs). To tackle this challenge, a fundamental research topic is the configuration of spike-timing and the exploration of more intricate architectures. In this work, we demonstrate a learnable axonal delay combined with local skip-connections yields state-of-the-art performance on challenging benchmarks for spoken word recognition. Additionally, we introduce an auxiliary loss term to further enhance accuracy and stability. Experiments on the neuromorphic speech benchmark datasets, NTIDIDIGITS and SHD, show improvements in performance when incorporating our delay module in comparison to vanilla feedforward SNNs. Specifically, with the integration of our delay module, the performance on NTIDIDIGITS and SHD improves by 14% and 18%, respectively. When paired with local skip-connections and the auxiliary loss, our approach surpasses both recurrent and convolutional neural networks, yet uses 10 × fewer parameters for NTIDIDIGITS and 7 × fewer for SHD.

Brain-guided manifold transferring to improve the performance of spiking neural networks in image classification.

Spiking neural networks (SNNs), as the third generation of neural networks, are based on biological models of human brain neurons. In this work, a shallow SNN plays the role of an explicit image decoder in the image classification. An LSTM-based EEG encoder is used to construct the EEG-based feature space, which is a discriminative space in viewpoint of classification accuracy by SVM. Then, the visual feature vectors extracted from SNN is mapped to the EEG-based discriminative features space by manifold transferring based on mutual k-Nearest Neighbors (Mk-NN MT). This proposed "Brain-guided system" improves the separability of the SNN-based visual feature space. In the test phase, the spike patterns extracted by SNN from the input image is mapped to LSTM-based EEG feature space, and then classified without need for the EEG signals. The SNN-based image encoder is trained by the conversion method and the results are evaluated and compared with other training methods on the challenging small ImageNet-EEG dataset. Experimental results show that the proposed transferring the manifold of the SNN-based feature space to LSTM-based EEG feature space leads to 14.25% improvement at most in the accuracy of image classification. Thus, embedding SNN in the brain-guided system which is trained on a small set, improves its performance in image classification.

The Effects of Biological Constraints on the Performance of Spiking Neural Networks

The Effects of Biological Constraints on the Performance of Spiking Neural Networks

Investigation of social and cognitive predictors in non-transition ultra-high-risk’ individuals for psychosis using spiking neural networks

Finding predictors of social and cognitive impairment in non-transition Ultra-High-Risk individuals (UHR) is critical in prognosis and planning of potential personalised intervention strategies. Social and cognitive functioning observed in youth at UHR for psychosis may be protective against transition to clinically relevant illness. The current study used a computational method known as Spiking Neural Network (SNN) to identify the cognitive and social predictors of transitioning outcome. Participants (90 UHR, 81 Healthy Control (HC)) completed batteries of neuropsychological tests in the domains of verbal memory, working memory, processing speed, attention, executive function along with social skills-based performance at baseline and 4 × 6-month follow-up intervals. The UHR status was recorded as Remitters, Converters or Maintained. SNN were used to model interactions between variables across groups over time and classify UHR status. The performance of SNN was examined relative to other machine learning methods. Higher interaction between social and cognitive variables was seen for the Maintained, than Remitter subgroup. Findings identified the most important cognitive and social variables (particularly verbal memory, processing speed, attention, affect and interpersonal social functioning) that showed discriminative patterns in the SNN models of HC vs UHR subgroups, with accuracies up to 80%; outperforming other machine learning models (56–64% based on 18 months data). This finding is indicative of a promising direction for early detection of social and cognitive impairment in UHR individuals that may not anticipate transition to psychosis and implicate early initiated interventions to stem the impact of clinical symptoms of psychosis.

Comparison of spiking neural networks with different topologies based on anti-disturbance ability under external noise

The research on robustness of brain-like models contributes to promoting its neural information processing ability, and the understanding of bio-brain function. However, the biological rationality of the current brain-like models is inadequate. In addition, the effect of network topologies on the robustness of brain-like models has not been clarified. In this study, inspired by the topological characteristics of biological functional brain networks, we construct five kinds of spiking neural networks (SNNs), which have the same Izhikevich neuron model and the same synaptic plasticity model with time-delay, but different network topologies. Then, the robustness of the SNNs with different topologies is comparatively assessed based on the anti-disturbance ability under different noise. Further, by taking a speech recognition task as the case study, we investigate the anti-disturbance ability of these SNNs in application. Finally, the anti-disturbance mechanism of the SNNs is discussed. Our simulation consistently certifies that: (i) In terms of anti-disturbance indicators, the complex SNN outperforms the small-world SNN, the small-world SNN outperforms the scale-free SNN, and all of them outperform the random SNN and the regular SNN, which indicates that the SNNs with more biological rationality have the better anti-disturbance ability. (ii) In terms of speech recognition accuracy, the performance of SNNs with different topologies presents the consistent order with the anti-disturbance ability above. And the recognition accuracy of these SNNs under disturbance still remains almost the same, compared with these SNNs without disturbance. (iii) The evolution process of neural information is clarified, which hints that the synaptic plasticity is the intrinsic factor of anti-disturbance ability, and the network topology is a factor that affects the anti-disturbance ability at the level of performance. Our simulation results are conducive to the design of neuromorphic algorithms with robustness on analog or mixed-signal neuromorphic chips under complex noise environment.

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.

Classification of Whisker Deflections From Evoked Responses in the Somatosensory Barrel Cortex With Spiking Neural Networks.

Spike-based neuromorphic hardware has great potential for low-energy brain-machine interfaces, leading to a novel paradigm for neuroprosthetics where spiking neurons in silicon read out and control activity of brain circuits. Neuromorphic processors can receive rich information about brain activity from both spikes and local field potentials (LFPs) recorded by implanted neural probes. However, it was unclear whether spiking neural networks (SNNs) implemented on such devices can effectively process that information. Here, we demonstrate that SNNs can be trained to classify whisker deflections of different amplitudes from evoked responses in a single barrel of the rat somatosensory cortex. We show that the classification performance is comparable or even superior to state-of-the-art machine learning approaches. We find that SNNs are rather insensitive to recorded signal type: both multi-unit spiking activity and LFPs yield similar results, where LFPs from cortical layers III and IV seem better suited than those of deep layers. In addition, no hand-crafted features need to be extracted from the data—multi-unit activity can directly be fed into these networks and a simple event-encoding of LFPs is sufficient for good performance. Furthermore, we find that the performance of SNNs is insensitive to the network state—their performance is similar during UP and DOWN states.

Spiking Neural Networks: A Survey

The field of Deep Learning (DL) has seen a remarkable series of developments with increasingly accurate and robust algorithms. However, the increase in performance has been accompanied by an increase in the parameters, complexity, and training and inference time of the models, which means that we are rapidly reaching a point where DL may no longer be feasible. On the other hand, some specific applications need to be carefully considered when developing DL models due to hardware limitations or power requirements. In this context, there is a growing interest in efficient DL algorithms, with Spiking Neural Networks (SNNs) being one of the most promising paradigms. Due to the inherent asynchrony and sparseness of spike trains, these types of networks have the potential to reduce power consumption while maintaining relatively good performance. This is attractive for efficient DL and if successful, could replace traditional Artificial Neural Networks (ANNs) in many applications. However, despite significant progress, the performance of SNNs on benchmark datasets is often lower than that of traditional ANNs. Moreover, due to the non-differentiable nature of their activation functions, it is difficult to train SNNs with direct backpropagation, so appropriate training strategies must be found. Nevertheless, significant efforts have been made to develop competitive models. This survey covers the main ideas behind SNNs and reviews recent trends in learning rules and network architectures, with a particular focus on biologically inspired strategies. It also provides some practical considerations of state-of-the-art SNNs and discusses relevant research opportunities.

Neural heterogeneity promotes robust learning

The brain is a hugely diverse, heterogeneous structure. Whether or not heterogeneity at the neural level plays a functional role remains unclear, and has been relatively little explored in models which are often highly homogeneous. We compared the performance of spiking neural networks trained to carry out tasks of real-world difficulty, with varying degrees of heterogeneity, and found that heterogeneity substantially improved task performance. Learning with heterogeneity was more stable and robust, particularly for tasks with a rich temporal structure. In addition, the distribution of neuronal parameters in the trained networks is similar to those observed experimentally. We suggest that the heterogeneity observed in the brain may be more than just the byproduct of noisy processes, but rather may serve an active and important role in allowing animals to learn in changing environments.

Accurate and efficient time-domain classification with adaptive spiking recurrent neural networks

Inspired by detailed modelling of biological neurons, spiking neural networks (SNNs) are investigated as biologically plausible and high-performance models of neural computation. The sparse and binary communication between spiking neurons potentially enables powerful and energy-efficient neural networks. The performance of SNNs, however, has remained lacking compared with artificial neural networks. Here we demonstrate how an activity-regularizing surrogate gradient combined with recurrent networks of tunable and adaptive spiking neurons yields the state of the art for SNNs on challenging benchmarks in the time domain, such as speech and gesture recognition. This also exceeds the performance of standard classical recurrent neural networks and approaches that of the best modern artificial neural networks. As these SNNs exhibit sparse spiking, we show that they are theoretically one to three orders of magnitude more computationally efficient compared to recurrent neural networks with similar performance. Together, this positions SNNs as an attractive solution for AI hardware implementations. The use of sparse signals in spiking neural networks, modelled on biological neurons, offers in principle a highly efficient approach for artificial neural networks when implemented on neuromorphic hardware, but new training approaches are needed to improve performance. Using a new type of activity-regularizing surrogate gradient for backpropagation combined with recurrent networks of tunable and adaptive spiking neurons, state-of-the-art performance for spiking neural networks is demonstrated on benchmarks in the time domain.

The Heidelberg Spiking Data Sets for the Systematic Evaluation of Spiking Neural Networks.

Spiking neural networks are the basis of versatile and power-efficient information processing in the brain. Although we currently lack a detailed understanding of how these networks compute, recently developed optimization techniques allow us to instantiate increasingly complex functional spiking neural networks in-silico. These methods hold the promise to build more efficient non-von-Neumann computing hardware and will offer new vistas in the quest of unraveling brain circuit function. To accelerate the development of such methods, objective ways to compare their performance are indispensable. Presently, however, there are no widely accepted means for comparing the computational performance of spiking neural networks. To address this issue, we introduce two spike-based classification data sets, broadly applicable to benchmark both software and neuromorphic hardware implementations of spiking neural networks. To accomplish this, we developed a general audio-to-spiking conversion procedure inspired by neurophysiology. Furthermore, we applied this conversion to an existing and a novel speech data set. The latter is the free, high-fidelity, and word-level aligned Heidelberg digit data set that we created specifically for this study. By training a range of conventional and spiking classifiers, we show that leveraging spike timing information within these data sets is essential for good classification accuracy. These results serve as the first reference for future performance comparisons of spiking neural networks.

Optical Axons for Electro-Optical Neural Networks.

Recently, neuromorphic sensors, which convert analogue signals to spiking frequencies, have been reported for neurorobotics. In bio-inspired systems these sensors are connected to the main neural unit to perform post-processing of the sensor data. The performance of spiking neural networks has been improved using optical synapses, which offer parallel communications between the distanced neural areas but are sensitive to the intensity variations of the optical signal. For systems with several neuromorphic sensors, which are connected optically to the main unit, the use of optical synapses is not an advantage. To address this, in this paper we propose and experimentally verify optical axons with synapses activated optically using digital signals. The synaptic weights are encoded by the energy of the stimuli, which are then optically transmitted independently. We show that the optical intensity fluctuations and link’s misalignment result in delay in activation of the synapses. For the proposed optical axon, we have demonstrated line of sight transmission over a maximum link length of 190 cm with a delay of 8 μs. Furthermore, we show the axon delay as a function of the illuminance using a fitted model for which the root mean square error (RMS) similarity is 0.95.

Noise Helps Optimization Escape From Saddle Points in the Synaptic Plasticity.

Numerous experimental studies suggest that noise is inherent in the human brain. However, the functional importance of noise remains unknown. n particular, from a computational perspective, such stochasticity is potentially harmful to brain function. In machine learning, a large number of saddle points are surrounded by high error plateaus and give the illusion of the existence of local minimum. As a result, being trapped in the saddle points can dramatically impair learning and adding noise will attack such saddle point problems in high-dimensional optimization, especially under the strict saddle condition. Motivated by these arguments, we propose one biologically plausible noise structure and demonstrate that noise can efficiently improve the optimization performance of spiking neural networks based on stochastic gradient descent. The strict saddle condition for synaptic plasticity is deduced, and under such conditions, noise can help optimization escape from saddle points on high dimensional domains. The theoretical results explain the stochasticity of synapses and guide us on how to make use of noise. In addition, we provide biological interpretations of proposed noise structures from two points: one based on the free energy principle in neuroscience and another based on observations of in vivo experiments. Our simulation results manifest that in the learning and test phase, the accuracy of synaptic sampling with noise is almost 20% higher than that without noise for synthesis dataset, and the gain in accuracy with/without noise is at least 10% for the MNIST and CIFAR-10 dataset. Our study provides a new learning framework for the brain and sheds new light on deep noisy spiking neural networks.

SIES: A Novel Implementation of Spiking Convolutional Neural Network Inference Engine on Field-Programmable Gate Array

Neuromorphic computing is considered to be the future of machine learning, and it provides a new way of cognitive computing. Inspired by the excellent performance of spiking neural networks (SNNs) on the fields of low-power consumption and parallel computing, many groups tried to simulate the SNN with the hardware platform. However, the efficiency of training SNNs with neuromorphic algorithms is not ideal enough. Facing this, Michael et al. proposed a method which can solve the problem with the help of DNN (deep neural network). With this method, we can easily convert a well-trained DNN into an SCNN (spiking convolutional neural network). So far, there is a little of work focusing on the hardware accelerating of SCNN. The motivation of this paper is to design an SNN processor to accelerate SNN inference for SNNs obtained by this DNN-to-SNN method. We propose SIES (Spiking Neural Network Inference Engine for SCNN Accelerating). It uses a systolic array to accomplish the task of membrane potential increments computation. It integrates an optional hardware module of max-pooling to reduce additional data moving between the host and the SIES. We also design a hardware data setup mechanism for the convolutional layer on the SIES with which we can minimize the time of input spikes preparing. We implement the SIES on FPGA XCVU440. The number of neurons it supports is up to 4 000 while the synapses are 256 000. The SIES can run with the working frequency of 200 MHz, and its peak performance is 1.562 5 TOPS.

Effects of synaptic integration on the dynamics and computational performance of spiking neural network

Neurons in the brain receive thousands of synaptic inputs from other neurons. This afferent information is processed by neurons through synaptic integration, which is an important information processing mechanism in biological neural networks. Synaptic currents integrated from spiking trains of presynaptic neurons have complex nonlinear dynamics which endow neurons with significant computational abilities. However, in many computational studies of neural networks, external input currents are often simply taken as a direct current that is static. In this paper, the influences of synaptic and noise external currents on the dynamics of spiking neural network and its computational capability have been investigated in detail. Our results show that due to the nonlinear synaptic integration, both of fast and slow excitatory synaptic currents have much more complex and oscillatory fluctuations than the noise current with the same average intensity. Thus network driven by synaptic external current exhibits remarkably more complex dynamics than that driven by noise external current. Interestingly, the enhancement of network activity is beneficial for information transmission, which is further supported by two computational tasks conducted on the liquid state machine (LSM) network. LSM with synaptic external current displays considerably better performance in both nonlinear fitting and pattern classification than that with noise external current. Synaptic integration can significantly enhance the entropy of activity patterns and computational performance of LSM. Our results demonstrate that the complex dynamics of nonlinear synaptic integration play a critical role in the computational abilities of neural networks and should be more broadly considered in the modelling studies of spiking neural networks.

Classifying Melanoma Skin Lesions Using Convolutional Spiking Neural Networks With Unsupervised STDP Learning Rule

Deep learning methods have made some achievements in the automatic skin lesion recognition, but there are still some problems such as limited training samples, too complicated network structure, and expensive computational costs. Considering the inherent power-efficiency, biological plausibility and good image recognition performance of spiking neural networks (SNNs), in this paper we make malignant melanoma and benign melanocytic nevi skin lesions classification using convolutional SNNs with unsupervised spike-timing-dependent plasticity (STDP) learning rule. Efficient temporal coding, event driven learning rule and winner-take-all (WTA) mechanism together ensure sparse spike coding and efficient learning of our networks which achieve an average accuracy of 83.8%. We further propose to use feature selection to select more diagnostic features to improve the classification performance of our networks. Our SNNs with feature selection reach an average accuracy of 87.7%. Experimental results show that comparing to CNNs that need to be trained from scratch, our SNNs (with and without feature selection) not only achieve much better classification accuracies but also have much better runtime efficiency. Moreover, although the pretrained CNNs models can achieve similar running time, our proposed SNNs are more stable and easier to use than the pretrained CNNs because we do not need to try many pretrained models any more, and our SNNs also have much better classification accuracies than the pretrained CNNs. In addition, our networks have only three convolutional layers, and the complexity of the model and the parameters that need to be trained in the networks are greatly reduced. Our works show that STDP-based SNNs are very beneficial for the implementation of automated skin lesion classifiers on small portable devices.

Character recognition from trajectory by recurrent spiking neural networks.

Spiking neural networks are biologically plausible and power-efficient on neuromorphic hardware, while recurrent neural networks have been proven to be efficient on time series data. However, how to use the recurrent property to improve the performance of spiking neural networks is still a problem. This paper proposes a recurrent spiking neural network for character recognition using trajectories. In the network, a new encoding method is designed, in which varying time ranges of input streams are used in different recurrent layers. This is able to improve the generalization ability of our model compared with general encoding methods. The experiments are conducted on four groups of the character data set from University of Edinburgh. The results show that our method can achieve a higher average recognition accuracy than existing methods.

Relative ordering learning in spiking neural network for pattern recognition

A learning rule based on the relative ordering of output spikes is proposed.The learning rule adjusts output spikes dynamically and adaptively.With low training cost, great generalization ability and robustness are achieved. The timing of spikes plays an important role in the information processing of brain. However, for temporal-based learning algorithms, the temporally precise spike as learning target is not able to fit with the variety of stimuli. The performance of spiking neural networks (SNNs) is adversely affected by fixed target spikes. This paper proposes a new learning rule called relative ordering learning (ROL) for SNNs. In contrast to the existing algorithms that drive a neuron to fire or not fire or to fire at precise times, the ROL rule trains the neuron to emit the first spike to respond to the associated stimuli. Without the limitation of specified precise firing times, the ROL rule can adjust output spikes to fit with the feature of input stimuli dynamically and adaptively. Our experiments have demonstrated the great generalization ability of the ROL rule and its robustness against noise. With a few neurons and ultra-low training cost, the network trained by the ROL rule achieved the classification accuracies of 98.1% and 93.8% for training on the Iris and MNIST datasets, respectively, and the accuracies for testing are 94.2% and 90.3%. The comparison with MLP network also shows the great attraction of the SNN trained by the ROL rule as a solution for fast and efficient recognition tasks.