Results 61 to 70 of about 75,067 (283)
, 2017 Information in neural networks is represented as weighted connections, or synapses, between neurons. This poses a problem as the primary computational bottleneck for neural networks is the vector-matrix multiply when inputs are multiplied by the neural ...
Aimone, James B. +9 more
core +1 more source
Stochastic Synapses Enable Efficient Brain-Inspired Learning Machines [PDF]
, 2016 Recent studies have shown that synaptic unreliability is a robust and sufficient mechanism for inducing the stochasticity observed in cortex. Here, we introduce Synaptic Sampling Machines, a class of neural network models that uses synaptic stochasticity
Al-Shedivat, Maruan +4 more
core +2 more sources
Developmental and Epileptic Encephalopathy due to Biallelic Pathogenic Variants in PIGM
Annals of Clinical and Translational Neurology, EarlyView.ABSTRACT Objective PIGM encodes a critical enzyme in the glycosylphosphatidylinositol (GPI)‐anchor biosynthesis pathway. While promoter‐region mutations in PIGM have been associated with a relatively mild phenotype characterized by portal vein thrombosis and absence seizures, recent evidence suggests that coding‐region mutations result in a more severe
Júlia Sala‐Coromina +11 more
wiley +1 more source
Advanced Electronic MaterialsThe biological photoreceptors in the retina convert light information into spikes, inspiring the emergence of artificial photoelectric spiking neurons. However, due to the lack of biocompatible and biodegradable characteristics, artificial photoelectric ...
Yaxiong Cao +8 more
doaj +1 more source
Gradient Descent Learning Algorithm for Spiking Neuron with Delay Adjustment [PDF]
Jisuanji gongcheng, 2019 The spiking neuron supervised learning algorithm adjusts the synaptic weight of the neuron by gradient descent method,but the accuracy gets low and the learning period gets long as the length of the target learning sequence increases.Therefore,a gradient
YANG Jing, XU Yan, ZHAO Xin
doaj +1 more source
Deep Neural Networks - A Brief History
, 2017 Introduction to deep neural networks and their history.Comment: 14 pages, 14 ...
AL Hodgkin +13 more
core +1 more source
In-phase and anti-phase synchronization in noisy Hodgkin-Huxley neurons [PDF]
, 2013 We numerically investigate the influence of intrinsic channel noise on the dynamical response of delay-coupling in neuronal systems. The stochastic dynamics of the spiking is modeled within a stochastic modification of the standard Hodgkin-Huxley model ...
Ao, Xue, Hanggi, Peter, Schmid, Gerhard
core +2 more sources
Epilepsy‐Associated Variants of a Single SCN1A Codon Exhibit Divergent Functional Properties
Annals of Clinical and Translational Neurology, EarlyView.ABSTRACT Objective Pathogenic variants in SCN1A, which encodes the voltage‐gated sodium channel NaV1.1, are associated with multiple epilepsy syndromes exhibiting a range of clinical severity. SCN1A variants are reported in different syndromes, including Dravet syndrome, which is associated with loss‐of‐function, whereas neonatal/infantile‐onset ...
Lanie N. Liebovitz +3 more
wiley +1 more source
Advanced Intelligent Systems, 2022 Developing an energy‐efficient artificial sensory system is of great significance for neuroprosthesis, neurorobotics, and intelligent human–machine interfaces.
Shuai Zhong +4 more
doaj +1 more source
A neural circuit for navigation inspired by C. elegans Chemotaxis [PDF]
, 2014 We develop an artificial neural circuit for contour tracking and navigation inspired by the chemotaxis of the nematode Caenorhabditis elegans. In order to harness the computational advantages spiking neural networks promise over their non-spiking ...
Rajendran, Bipin, Santurkar, Shibani
core