Results 61 to 70 of about 28,095 (262)

A Synaptic Pruning-Based Spiking Neural Network for Hand-Written Digits Classification

Frontiers in Artificial Intelligence, 2022
A spiking neural network model inspired by synaptic pruning is developed and trained to extract features of hand-written digits. The network is composed of three spiking neural layers and one output neuron whose firing rate is used for classification ...
Faramarz Faghihi, Hany Alashwal, Ahmed A. Moustafa, Ahmed A. Moustafa   +3 more
doaj   +1 more source

Solution‐Processed Two‐Dimensional Indium Oxide on Sodium‐Embedded Alumina for Reconfigurable Optoelectronic Synaptic Transistors

Advanced Functional Materials, EarlyView.
Wafer‐scale two‐dimensioanl In2Se3 oxidized into InOx on sodium‐embedded beta‐alumina enables multifunctional reconfigurable electronics. Sodium ions accumulate within distinct spatial distribution under drain‐controlle and gate‐controlled operation. Drain‐control operation gives controllability of ultraviolet‐driven optoelectronic synaptic conductance
Jinhong Min, Yonghyun Albert Kwon, Hyunbin Kim, Jihyun Kim, Myeongjin Jung, Jaewon Heo, Gwang Ya Kim, Vlastimil Mazanek, Zdeněk Sofer, In Soo Kim, Jeong Ho Cho, Hyesung Park, Sang Min Won, Joohoon Kang   +13 more
wiley   +1 more source

Comparison of FORCE trained spiking and rate neural networks shows spiking networks learn slowly with noisy, cross-trial firing rates.

PLoS Computational Biology
Training spiking recurrent neural networks (SRNNs) presents significant challenges compared to standard recurrent neural networks (RNNs) that model neural firing rates more directly.
Thomas Robert Newton, Wilten Nicola
doaj   +1 more source

Implantable Ionic Memristors Based on Natural Polymer Heterojunctions

Advanced Functional Materials, EarlyView.
We report an implantable natural polymer‐based ionic memristor composed of hyaluronic acid, chitosan, and PDMS. The device achieved 98.94% accuracy in MNIST classification while reducing training time by 36.8% compared with a conventional artificial neural network (ANN).
Dong‐yup Lee, Byung Ik Park, Gihyeon Yim, Hyunjae Yoo, Sangjun Ma, Jundong Park, Jeong‐Yun Sun   +6 more
wiley   +1 more source

A Spiking Neuron and Population Model Based on the Growth Transform Dynamical System

Frontiers in Neuroscience, 2020
In neuromorphic engineering, neural populations are generally modeled in a bottom-up manner, where individual neuron models are connected through synapses to form large-scale spiking networks.
Ahana Gangopadhyay, Darshit Mehta, Shantanu Chakrabartty   +2 more
doaj   +1 more source

Performance Enhancement of Tin Chloride‐Incorporated Ferroelectric Polymer‐Based Artificial Synapse for Hardware Neural Networks

Advanced Functional Materials, EarlyView.
This paper proposes a highly efficient ferroelectric artificial synapse device based on an oxide semiconductor and SnCl2‐inserted P(VDF‐TrFE) gate dielectric layer. This FeFET significantly improved the synaptic performance due to the ion‐dipole interaction.
Hyun‐Soo Kim, Hyunkyu Lee, Yeonho Choi, Won Young Jang, Hyungmin Kim, Krishna Moorthy Ponnusamy, Hongseung Lee, Jaewook Yoo, Ji Ye Lee, S. Chandramohan, Seongin Hong, Hagyoul Bae, Hyeon‐Sik Jang, Sang Yeol Lee, Keun Heo   +14 more
wiley   +1 more source

High-performance deep spiking neural networks with 0.3 spikes per neuron

Nature Communications
Communication by rare, binary spikes is a key factor for the energy efficiency of biological brains. However, it is harder to train biologically-inspired spiking neural networks than artificial neural networks.
Ana Stanojevic, Stanisław Woźniak, Guillaume Bellec, Giovanni Cherubini, Angeliki Pantazi, Wulfram Gerstner   +5 more
doaj   +1 more source

Magnesium‐Based Transient Bioelectronics, Bio‐Optics and Bio‐Scaffolds

Advanced Functional Materials, EarlyView.
This paper reviews the state of the art and recent advances in magnesium‐based thin‐film, foils, and scaffolds for applications in transient bio‐optics, bioelectronics and tissue engineering. The design principles, fabrication methods, material properties, and integration strategies are discussed in detail.
Massimo Mariello, Yves Leterrier
wiley   +1 more source

BindsNET: A Machine Learning-Oriented Spiking Neural Networks Library in Python

Frontiers in Neuroinformatics, 2018
The development of spiking neural network simulation software is a critical component enabling the modeling of neural systems and the development of biologically inspired algorithms.
Hananel Hazan, Daniel J. Saunders, Hassaan Khan, Devdhar Patel, Darpan T. Sanghavi, Hava T. Siegelmann, Robert Kozma   +6 more
doaj   +1 more source

Phase diagram of spiking neural networks [PDF]

Frontiers in Computational Neuroscience, 2015
In computer simulations of spiking neural networks, often it is assumed that every two neurons of the network are connected by a probability of 2\%, 20\% of neurons are inhibitory and 80\% are excitatory. These common values are based on experiments, observations, and trials and errors, but here, I take a different perspective, inspired by evolution, I
openaire   +4 more sources