Related papers: Spiking Deep Networks with LIF Neurons
The synergy between spiking neural networks and neuromorphic hardware holds promise for the development of energy-efficient AI applications. Inspired by this potential, we revisit the foundational aspects to study the capabilities of…
Leaky integrate-and-fire (LIF) models are mean-field limits, with a large number of neurons, used to describe neural networks. We consider inhomogeneous networks structured by a connec-tivity parameter (strengths of the synaptic weights)…
The brain is the perfect place to look for inspiration to develop more efficient neural networks. The inner workings of our synapses and neurons provide a glimpse at what the future of deep learning might look like. This paper serves as a…
Training deep neural networks with the error backpropagation algorithm is considered implausible from a biological perspective. Numerous recent publications suggest elaborate models for biologically plausible variants of deep learning,…
Leaky integrate-and-fire (LIF) networks are standard reduced models for spike-based neural dynamics and a natural substrate for neuromorphic computation. We study time-driven Euler--Maruyama simulation of current-based LIF networks with…
With the continued innovations of deep neural networks, spiking neural networks (SNNs) that more closely resemble biological brain synapses have attracted attention owing to their low power consumption.However, for continuous data values,…
Spiking neural networks (SNNs) have received significant attention for their biological plausibility. SNNs theoretically have at least the same computational power as traditional artificial neural networks (ANNs). They possess potential of…
An analytical description of the response properties of simple but realistic neuron models in the presence of noise is still lacking. We determine completely up to the second order the firing statistics of a single and a pair of leaky…
Stability arguments are often used to prevent learning algorithms from having ever increasing activity and weights that hinder generalization. However, stability conditions can clash with the sparsity required to augment the energy…
Compared with rate-based artificial neural networks, Spiking Neural Networks (SNN) provide a more biological plausible model for the brain. But how they perform supervised learning remains elusive. Inspired by recent works of Bengio et al.,…
Spiking neural networks offer low energy consumption due to their event-driven nature. Beyond binary spike outputs, their intrinsic floating-point dynamics merit greater attention. Neuronal threshold levels and reset modes critically…
Spiking neural networks (SNNs) are bio-inspired neural networks with asynchronous discrete and sparse characteristics, which have increasingly manifested their superiority in low energy consumption. Recent research is devoted to utilizing…
The brain-inspired Spiking Neural Networks (SNNs) have garnered considerable research interest due to their superior performance and energy efficiency in processing temporal signals. Recently, a novel multi-compartment spiking neuron model,…
Spiking Neural Networks (SNNs) that operate in an event-driven manner and employ binary spike representation have recently emerged as promising candidates for energy-efficient computing. However, a cost bottleneck arises in obtaining…
Spiking neural network (SNN) is interesting due to its strong bio-plausibility and high energy efficiency. However, its performance is falling far behind conventional deep neural networks (DNNs). In this paper, considering a general class…
Spiking neural networks (SNNs) are a promising paradigm for energy-efficient computation, yet their theoretical foundations-especially regarding stability and robustness-remain limited compared to artificial neural networks. In this work,…
Tiny Machine Learning (TinyML) has become a growing field in on-device processing for Internet of Things (IoT) applications, capitalizing on AI algorithms that are optimized for their low complexity and energy efficiency. These algorithms…
U-Net, known for its simple yet efficient architecture, is widely utilized for image processing tasks and is particularly suitable for deployment on neuromorphic chips. This paper introduces the novel concept of Spiking-UNet for image…
The computational complexity of deep learning algorithms has given rise to significant speed and memory challenges for the execution hardware. In energy-limited portable devices, highly efficient processing platforms are indispensable for…
Limitations in processing capabilities and memory of today's computers make spiking neuron-based (human) whole-brain simulations inevitably characterized by a compromise between bio-plausibility and computational cost. It translates into…