Statistical Description of Electrophysiological Features of Neurons across Layers of Human Cortex

Panda, Subhasis; Hore, Archita; Chakraborty, Ayan; Chakrabarti, Saswat

doi:10.1109/acts53447.2021.9708234

Cited by 1 publication

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, recent studies have shown that biological neurons can generate several spiking dynamics and they can fire spikes of different amplitudes and duration (Chakraborty et al, 2022). Moreover, in contrast to the structure of the human cortex (Panda et al, 2021), we only consider networks composed of layers of neurons with identical characteristics. The integrate-and-fire model used in this paper does take into account only a limited set of features of the biological neuron.…”

Section: State Of the Artmentioning

confidence: 99%

Trainable quantization for Speedy Spiking Neural Networks

2023

View full text Add to dashboard Cite

Spiking neural networks are considered as the third generation of Artificial Neural Networks. SNNs perform computation using neurons and synapses that communicate using binary and asynchronous signals known as spikes. They have attracted significant research interest over the last years since their computing paradigm allows theoretically sparse and low-power operations. This hypothetical gain, used from the beginning of the neuromorphic research, was however limited by three main factors: the absence of an efficient learning rule competing with the one of classical deep learning, the lack of mature learning framework, and an important data processing latency finally generating energy overhead. While the first two limitations have recently been addressed in the literature, the major problem of latency is not solved yet. Indeed, information is not exchanged instantaneously between spiking neurons but gradually builds up over time as spikes are generated and propagated through the network. This paper focuses on quantization error, one of the main consequence of the SNN discrete representation of information. We argue that the quantization error is the main source of accuracy drop between ANN and SNN. In this article we propose an in-depth characterization of SNN quantization noise. We then propose a end-to-end direct learning approach based on a new trainable spiking neural model. This model allows adapting the threshold of neurons during training and implements efficient quantization strategies. This novel approach better explains the global behavior of SNNs and minimizes the quantization noise during training. The resulting SNN can be trained over a limited amount of timesteps, reducing latency, while beating state of the art accuracy and preserving high sparsity on the main datasets considered in the neuromorphic community.

show abstract

Section: State Of the Artmentioning

confidence: 99%