Exploring neuromorphic computing based on spiking neural networks: Algorithms to hardware

N Rathi, I Chakraborty, A Kosta, A Sengupta… - ACM Computing …, 2023 - dl.acm.org
Neuromorphic Computing, a concept pioneered in the late 1980s, is receiving a lot of
attention lately due to its promise of reducing the computational energy, latency, as well as …

Recurrent neural networks as versatile tools of neuroscience research

O Barak - Current opinion in neurobiology, 2017 - Elsevier
Highlights•Recurrent neural networks (RNNs) are powerful models of neural systems.•RNNs
can be either designed or trained to perform a task.•In both cases, low dimensional …

Long short-term memory and learning-to-learn in networks of spiking neurons

G Bellec, D Salaj, A Subramoney… - Advances in neural …, 2018 - proceedings.neurips.cc
Recurrent networks of spiking neurons (RSNNs) underlie the astounding computing and
learning capabilities of the brain. But computing and learning capabilities of RSNN models …

[HTML][HTML] Toward an integration of deep learning and neuroscience

AH Marblestone, G Wayne, KP Kording - Frontiers in computational …, 2016 - frontiersin.org
Neuroscience has focused on the detailed implementation of computation, studying neural
codes, dynamics and circuits. In machine learning, however, artificial neural networks tend …

The centrality of population-level factors to network computation is demonstrated by a versatile approach for training spiking networks

B DePasquale, D Sussillo, LF Abbott, MM Churchland - Neuron, 2023 - cell.com
Neural activity is often described in terms of population-level factors extracted from the
responses of many neurons. Factors provide a lower-dimensional description with the aim of …

Supervised learning in spiking neural networks with FORCE training

W Nicola, C Clopath - Nature communications, 2017 - nature.com
Populations of neurons display an extraordinary diversity in the behaviors they affect and
display. Machine learning techniques have recently emerged that allow us to create …

Building functional networks of spiking model neurons

LF Abbott, B DePasquale, RM Memmesheimer - Nature neuroscience, 2016 - nature.com
Most of the networks used by computer scientists and many of those studied by modelers in
neuroscience represent unit activities as continuous variables. Neurons, however …

Motor cortex activity across movement speeds is predicted by network-level strategies for generating muscle activity

S Saxena, AA Russo, J Cunningham, MM Churchland - Elife, 2022 - elifesciences.org
Learned movements can be skillfully performed at different paces. What neural strategies
produce this flexibility? Can they be predicted and understood by network modeling? We …

Predicting non-linear dynamics by stable local learning in a recurrent spiking neural network

A Gilra, W Gerstner - Elife, 2017 - elifesciences.org
The brain needs to predict how the body reacts to motor commands, but how a network of
spiking neurons can learn non-linear body dynamics using local, online and stable learning …

Simple framework for constructing functional spiking recurrent neural networks

R Kim, Y Li, TJ Sejnowski - Proceedings of the national …, 2019 - National Acad Sciences
Cortical microcircuits exhibit complex recurrent architectures that possess dynamically rich
properties. The neurons that make up these microcircuits communicate mainly via discrete …