The autoencoder algorithm is a simple but powerful unsupervised method for training neural networks. Autoencoder networks can learn sparse distributed codes similar to those seen in cortical sensory areas such as visual area V1, but they can also be ...
Neural associative networks are a promising computational paradigm for both modeling neural circuits of the brain and implementing associative memory and Hebbian cell assemblies in parallel VLSI or nanoscale hardware. Previous work has extensively in...
Advanced materials (Deerfield Beach, Fla.)
Nov 17, 2015
Metaplasticity, a higher order of synaptic plasticity, as well as a key issue in neuroscience, is realized with artificial synapses based on a WO3 thin film, and the activity-dependent metaplastic responses of the artificial synapses, such as spike-t...
Neural networks : the official journal of the International Neural Network Society
Nov 12, 2015
A central question in artificial intelligence is how to design agents capable of switching between different behaviors in response to environmental changes. Taking inspiration from neuroscience, we address this problem by utilizing artificial neural ...
Proceedings of the National Academy of Sciences of the United States of America
Oct 26, 2015
Grounding autonomous behavior in the nervous system is a fundamental challenge for neuroscience. In particular, self-organized behavioral development provides more questions than answers. Are there special functional units for curiosity, motivation, ...
Information encoding in the nervous system is supported through the precise spike timings of neurons; however, an understanding of the underlying processes by which such representations are formed in the first place remains an open question. Here we ...
International journal of neural systems
Oct 9, 2015
Synaptic plasticity is widely recognized to support adaptable information processing in the brain. Spike-timing-dependent plasticity, one subtype of plasticity, can lead to synchronous spike propagation with temporal spiking coding information. Recen...
IEEE transactions on bio-medical engineering
Oct 1, 2015
GOAL: In this study, we defined a realistic cerebellar model through the use of artificial spiking neural networks, testing it in computational simulations that reproduce associative motor tasks in multiple sessions of acquisition and extinction.
Journal of neuroengineering and rehabilitation
Sep 17, 2015
Robot-mediated therapy can help improve walking ability in patients following injuries to the central nervous system. However, the efficacy of this treatment varies between patients, and evidence for the mechanisms underlying functional improvements ...
Physical review. E, Statistical, nonlinear, and soft matter physics
Sep 14, 2015
In continuous attractor neural networks (CANNs), spatially continuous information such as orientation, head direction, and spatial location is represented by Gaussian-like tuning curves that can be displaced continuously in the space of the preferred...
Join thousands of healthcare professionals staying informed about the latest AI breakthroughs in medicine. Get curated insights delivered to your inbox.