Results 41 to 50 of about 3,555,912 (299)

Targeting operational regimes of interest in recurrent neural networks.

PLoS Computational Biology, 2023
Neural computations emerge from local recurrent neural circuits or computational units such as cortical columns that comprise hundreds to a few thousand neurons.
Pierre Ekelmans, Nataliya Kraynyukova, Tatjana Tchumatchenko   +2 more
doaj   +1 more source

A VLSI neuromorphic device for implementing spike-based neural networks [PDF]

, 2011
Indiveri G, Chicca E. A VLSI neuromorphic device for implementing spike-based neural networks. Presented at the Proceedings of the 21st Italian Workshop on Neural Nets (WIRN).We present a neuromorphic VLSI device which comprises hybrid analog/digital ...
Morabito, C. F., Indiveri, G., Apolloni, B., Esposito, A., Chicca, Elisabetta ; https://orcid.org/, Bassis, S.   +5 more
core   +1 more source

A Layered Spiking Neural System for Classification Problems [PDF]

, 2022
Biological brains have a natural capacity for resolving certain classification tasks. Studies on biologically plausible spiking neurons, architectures and mechanisms of artificial neural systems that closely match biological observations while giving ...
Neri, Ferrante, Rong, Haina, Zhang, Gexiang, Zhang, Xihai, Paul, Prithwineel, Ong, Yew-Soon, Zhu, Ming   +6 more
core   +1 more source

Exploiting device mismatch in neuromorphic VLSI systems to implement axonal delays [PDF]

, 2012
Axonal delays are used in neural computation to implement faithful models of biological neural systems, and in spiking neural networks models to solve computationally demanding tasks. While there is an increasing number of software simulations of spiking
Sadique Sheik, Sheik, S., Sheik, Sadique, Indiveri, G., Giacomo Indiveri, Elisabetta Chicca, Chicca, Elisabetta, Indiveri, Giacomo, Chicca, Elisabetta ; https://orcid.org/   +8 more
core   +1 more source

SNS-Toolbox: An Open Source Tool for Designing Synthetic Nervous Systems and Interfacing Them with Cyber–Physical Systems

Biomimetics, 2023
One developing approach for robotic control is the use of networks of dynamic neurons connected with conductance-based synapses, also known as Synthetic Nervous Systems (SNS).
William R. P. Nourse, Clayton Jackson, Nicholas S. Szczecinski, Roger D. Quinn   +3 more
doaj   +1 more source

A biologically inspired spiking model of visual processing for image feature detection [PDF]

, 2015
To enable fast reliable feature matching or tracking in scenes, features need to be discrete and meaningful, and hence edge or corner features, commonly called interest points are often used for this purpose.
Kerr, D, Coleman, S, Clogenson, M, McGinnity, TM   +3 more
core   +1 more source

Neural Architecture Search for Spiking Neural Networks

, 2022
Spiking Neural Networks (SNNs) have gained huge attention as a potential energy-efficient alternative to conventional Artificial Neural Networks (ANNs) due to their inherent high-sparsity activation. However, most prior SNN methods use ANN-like architectures (e.g., VGG-Net or ResNet), which could provide sub-optimal performance for temporal sequence ...
Youngeun Kim, Yuhang Li 0001, Hyoungseob Park, Yeshwanth Venkatesha, Priyadarshini Panda   +4 more
openaire   +4 more sources

Systematic construction of finite state automata using VLSI spiking neurons [PDF]

, 2012
Spiking neural networks implemented using electronic Very Large Scale Integration (VLSI) circuits are promising information processing architectures for carrying out complex cognitive tasks in real-world applications.
Neftci, Emre, Emre Neftci, Chicca, Elisabetta, Lepora, Nathan F., Rodney Douglas, Prescott, Tony J., Giacomo Indiveri, Verschure, Paul F. M. J., Jonathan Binas, Elisabetta Chicca, Binas, Jonathan, Indiveri, Giacomo, Mura, Anna, Chicca, Elisabetta ; https://orcid.org/, Douglas, Rodney   +14 more
core   +1 more source

Training Spiking Neural Networks for Reinforcement Learning Tasks With Temporal Coding Method

Frontiers in Neuroscience, 2022
Recent years witness an increasing demand for using spiking neural networks (SNNs) to implement artificial intelligent systems. There is a demand of combining SNNs with reinforcement learning architectures to find an effective training method.
Guanlin Wu, Dongchen Liang, Shaotong Luan, Ji Wang   +3 more
doaj   +1 more source

Deep learning in spiking neural networks [PDF]

Neural Networks, 2019
In recent years, deep learning has been a revolution in the field of machine learning, for computer vision in particular. In this approach, a deep (multilayer) artificial neural network (ANN) is trained in a supervised manner using backpropagation.
Kheradpisheh, Saeed Reza, Tavanaei, Amirhossein, Ghodrati, Masoud, Kheradpisheh, Saeed Reza, Masquelier, Timothée, Maida, Anthony   +5 more
openaire   +5 more sources