[HTML][HTML] Neuromorphic artificial intelligence systems

D Ivanov, A Chezhegov, D Larionov - Frontiers in Neuroscience, 2022‏ - frontiersin.org
Modern artificial intelligence (AI) systems, based on von Neumann architecture and classical
neural networks, have a number of fundamental limitations in comparison with the …

Temporal-wise attention spiking neural networks for event streams classification

M Yao, H Gao, G Zhao, D Wang… - Proceedings of the …, 2021‏ - openaccess.thecvf.com
How to effectively and efficiently deal with spatio-temporal event streams, where the events
are generally sparse and non-uniform and have the us temporal resolution, is of great value …

Liaf-net: Leaky integrate and analog fire network for lightweight and efficient spatiotemporal information processing

Z Wu, H Zhang, Y Lin, G Li, M Wang… - IEEE Transactions on …, 2021‏ - ieeexplore.ieee.org
Spiking neural networks (SNNs) based on the leaky integrate and fire (LIF) model have
been applied to energy-efficient temporal and spatiotemporal processing tasks. Due to the …

Sequence approximation using feedforward spiking neural network for spatiotemporal learning: Theory and optimization methods

X She, S Dash, S Mukhopadhyay - International Conference on …, 2021‏ - openreview.net
A dynamical system of spiking neurons with only feedforward connections can classify
spatiotemporal patterns without recurrent connections. However, the theoretical construct of …

Deep reinforcement learning with significant multiplications inference

DA Ivanov, DA Larionov, MV Kiselev, DV Dylov - Scientific Reports, 2023‏ - nature.com
We propose a sparse computation method for optimizing the inference of neural networks in
reinforcement learning (RL) tasks. Motivated by the processing abilities of the brain, this …

Asynchronous event processing with local-shift graph convolutional network

L Sun, Y Zhang, J Cheng, H Lu - … of the AAAI Conference on Artificial …, 2023‏ - ojs.aaai.org
Event cameras are bio-inspired sensors that produce sparse and asynchronous event
streams instead of frame-based images at a high-rate. Recent works utilizing graph …

Neuronflow: A hybrid neuromorphic–dataflow processor architecture for AI workloads

O Moreira, A Yousefzadeh, F Chersi… - 2020 2nd IEEE …, 2020‏ - ieeexplore.ieee.org
We present a novel computing architecture which combines the event-based and compute-
in-network principles of neuromorphic computing with a traditional dataflow architecture. The …

Heterogeneous neuronal and synaptic dynamics for spike-efficient unsupervised learning: Theory and design principles

B Chakraborty, S Mukhopadhyay - arxiv preprint arxiv:2302.11618, 2023‏ - arxiv.org
This paper shows that the heterogeneity in neuronal and synaptic dynamics reduces the
spiking activity of a Recurrent Spiking Neural Network (RSNN) while improving prediction …

Modeling learnable electrical synapse for high precision spatio-temporal recognition

Z Wu, Z Zhang, H Gao, J Qin, R Zhao, G Zhao, G Li - Neural Networks, 2022‏ - Elsevier
Bio-inspired recipes are being introduced to artificial neural networks for the efficient
processing of spatio-temporal tasks. Among them, Leaky Integrate and Fire (LIF) model is …

A TTFS-based energy and utilization efficient neuromorphic CNN accelerator

M Yu, T **ang, SP, KTN Chu… - Frontiers in …, 2023‏ - frontiersin.org
Spiking neural networks (SNNs), which are a form of neuromorphic, brain-inspired AI, have
the potential to be a power-efficient alternative to artificial neural networks (ANNs). Spikes …