They are 300 Poisson neurons, where the first 100 encode the whisker stimulus, the next 100 encode the auditory cue and the last 100 act as an extra noise source for our model. Out of the 300 neurons, 60 of them are inhibitory (red). The input neurons project unrestrictedly to the whole RSNN. The baseline firing rate of all input neurons is 5 Hz. The whisker stimulus and auditory cue are encoded with an increase of the firing rate for 10 ms, starting 4 ms after the onset of the actual stimuli.

Deep learning is a state-of-the-art methodology in numerous domains, including image recognition, natural language processing, and data generation [1]. The discovery of scaling laws in deep learning models [2, 3] has motivated the development of increasingly larger models, commonly referred to as foundation models [4, 5, 6]. Recent studies have shown that reasoning tasks can be improved through iterative computations during the inference phase [7]. While computational power continues to be a major driver of artificial intelligence (AI) advancements, the associated costs remain a significant barrier to broader adoption across diverse industries [8, 9]. This issue is especially critical in edge AI systems, where energy consumption is constrained by the limited capacity of batteries, making the need for more efficient computation paramount [10]. One promising strategy to enhance energy efficiency is fabricating dedicated hardware. Since matrixvector multiplication is the computational core in deep learning, parallelization greatly enhances computational efficiency [11]. Moreover, in data-driven applications such as deep learning, a substantial portion of power consumption is due to data movement between the processor and memory, commonly referred to as the von Neumann bottleneck [12].

This paper presents an efficient hardware implementation of the recently proposed Optimized Deep Event-driven Spiking Neural Network Architecture (ODESA). ODESA is the first network to have end-to-end multi-layer online local supervised training without using gradients and has the combined adaptation of weights and thresholds in an efficient hierarchical structure. This research shows that the network architecture and the online training of weights and thresholds can be implemented efficiently on a large scale in hardware. The implementation consists of a multi-layer Spiking Neural Network (SNN) and individual training modules for each layer that enable online self-learning without using back-propagation. By using simple local adaptive selection thresholds, a Winner-Takes-All (WTA) constraint on each layer, and a modified weight update rule that is more amenable to hardware, the trainer module allocates neuronal resources optimally at each layer without having to pass high-precision error measurements across layers. All elements in the system, including the training module, interact using event-based binary spikes. The hardware-optimized implementation is shown to preserve the performance of the original algorithm across multiple spatial-temporal classification problems with significantly reduced hardware requirements.

Brain-computer interfaces are being explored for a wide variety of therapeutic applications. Typically, this involves measuring and analyzing continuous-time electrical brain activity via techniques such as electrocorticogram (ECoG) or electroencephalography (EEG) to drive external devices. However, due to the inherent noise and variability in the measurements, the analysis of these signals is challenging and requires offline processing with significant computational resources. In this paper, we propose a simple yet efficient machine learning-based approach for the exemplary problem of hand gesture classification based on brain signals. We use a hybrid machine learning approach that uses a convolutional spiking neural network employing a bio-inspired event-driven synaptic plasticity rule for unsupervised feature learning of the measured analog signals encoded in the spike domain. We demonstrate that this approach generalizes to different subjects with both EEG and ECoG data and achieves superior accuracy in the range of 92.74-97.07% in identifying different hand gesture classes and motor imagery tasks.

As animals interact with their environments, they must constantly update estimates about their states. Bayesian models combine prior probabil- ities, a dynamical model and sensory evidence to update estimates op- timally. These models are consistent with the results of many diverse psychophysical studies. However, little is known about the neural rep- resentation and manipulation of such Bayesian information, particularly in populations of spiking neurons. We consider this issue, suggesting a model based on standard neural architecture and activations.

There's a supervised learning algorithm for SNN that enables a single neuron to learn spike pattern associations of input-output spike sequences at the precise times of spikes. This algorithm is termed SPAN(Spike Pattern Association Neuron). Anyone can build SNN to associate the input to output temporal patterns of desired spike sequences using this SPAN neuron. Here the input, output, and desired spike trains are transformed into analog signals by convolving the spikes with a kernel function. This transformation simplifies the computation of the error signal and, therefore, allows the application of gradient descent to optimize the synaptic weights.

High energy consumption and the increasing computational cost of Artificial Neural Network (ANN) training 1 tend to be prohibitive. Furthermore, their difficulty and inability to learn even simple temporal tasks seem to trouble the research community. Nonetheless, one can observe natural intelligence with minuscule energy consumption, capable of creativity, problem-solving, and multitasking. Biological systems seem to have mastered information processing and response through natural evolution. The need to understand what makes them so effective and adapt these findings led to Spiking Neural Networks (SNNs). In this article, we will cover both the theory and a simplistic implementation of SNNs in PyTorch. Biological neuron cells do not behave like the neuron we use in ANNs. But what is it that makes them different?

In the past decade, advances in Artificial Neural Networks (ANNs) have allowed them to perform extremely well for a wide range of tasks. In fact, they have reached human parity when performing image recognition, for example. Unfortunately, the accuracy of these ANNs comes at the expense of a large number of cache and/or memory accesses and compute operations. Spiking Neural Networks (SNNs), a type of neuromorphic, or brain-inspired network, have recently gained significant interest as power-efficient alternatives to ANNs, because they are sparse, accessing very few weights, and typically only use addition operations instead of the more power-intensive multiply-and-accumulate (MAC) operations. The vast majority of neuromorphic hardware designs support rate-encoded SNNs, where the information is encoded in spike rates. Rate-encoded SNNs could be seen as inefficient as an encoding scheme because it involves the transmission of a large number of spikes. A more efficient encoding scheme, Time-To-First-Spike (TTFS) encoding, encodes information in the relative time of arrival of spikes. While TTFS-encoded SNNs are more efficient than rate-encoded SNNs, they have, up to now, performed poorly in terms of accuracy compared to previous methods. Hence, in this work, we aim to overcome the limitations of TTFS-encoded neuromorphic systems. To accomplish this, we propose: (1) a novel optimization algorithm for TTFS-encoded SNNs converted from ANNs and (2) a novel hardware accelerator for TTFS-encoded SNNs, with a scalable and low-power design. Overall, our work in TTFS encoding and training improves the accuracy of SNNs to achieve state-of-the-art results on MNIST MLPs, while reducing power consumption by 1.46$\times$ over the state-of-the-art neuromorphic hardware.