Exploring neuromorphic computing based on spiking neural networks: Algorithms to hardware
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 …
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 …
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
Recurrent networks of spiking neurons (RSNNs) underlie the astounding computing and
learning capabilities of the brain. But computing and learning capabilities of RSNN models …
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 …
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
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 …
responses of many neurons. Factors provide a lower-dimensional description with the aim of …
Supervised learning in spiking neural networks with FORCE training
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 …
display. Machine learning techniques have recently emerged that allow us to create …
Building functional networks of spiking model neurons
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 …
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
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 …
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 …
spiking neurons can learn non-linear body dynamics using local, online and stable learning …
Simple framework for constructing functional spiking recurrent neural networks
Cortical microcircuits exhibit complex recurrent architectures that possess dynamically rich
properties. The neurons that make up these microcircuits communicate mainly via discrete …
properties. The neurons that make up these microcircuits communicate mainly via discrete …