Results 1 to 10 of about 1,313,936 (143)

Synaptic metaplasticity in binarized neural networks [PDF]

Nature Communications, 2021
Deep neural networks usually rapidly forget the previously learned tasks while training new ones. Laborieux et al. propose a method for training binarized neural networks inspired by neuronal metaplasticity that allows to avoid catastrophic forgetting ...
Axel Laborieux, Maxence Ernoult, Tifenn Hirtzlin, Damien Querlioz   +3 more
doaj   +4 more sources

AresB-Net: accurate residual binarized neural networks using shortcut concatenation and shuffled grouped convolution [PDF]

PeerJ Computer Science, 2021
This article proposes a novel network model to achieve better accurate residual binarized convolutional neural networks (CNNs), denoted as AresB-Net.
HyunJin Kim
doaj   +4 more sources

Digital Biologically Plausible Implementation of Binarized Neural Networks With Differential Hafnium Oxide Resistive Memory Arrays [PDF]

Frontiers in Neuroscience, 2020
The brain performs intelligent tasks with extremely low energy consumption. This work takes its inspiration from two strategies used by the brain to achieve this energy efficiency: the absence of separation between computing and memory functions and ...
Tifenn Hirtzlin, Marc Bocquet, Bogdan Penkovsky, Jacques-Olivier Klein, Etienne Nowak, Elisa Vianello, Jean-Michel Portal, Damien Querlioz   +7 more
doaj   +4 more sources

Bimodal-Distributed Binarized Neural Networks [PDF]

Mathematics, 2022
Binary neural networks (BNNs) are an extremely promising method for reducing deep neural networks’ complexity and power consumption significantly. Binarization techniques, however, suffer from ineligible performance degradation compared to their full ...
Tal Rozen, Moshe Kimhi, Brian Chmiel, Avi Mendelson, Chaim Baskin   +4 more
doaj   +2 more sources

Implementation of binarized neural networks immune to device variation and voltage drop employing resistive random access memory bridges and capacitive neurons [PDF]

Commun Eng
Resistive Random Access Memories (ReRAM) arrays provides a promising basement to deploy neural network accelerators based on near or in memory computing.
Ezzadeen M, Majumdar A, Valorge O, Castellani N, Gherman V, Regis G, Giraud B, Noel J, Meli V, Bocquet M, Andrieu F, Querlioz D, Portal J.   +12 more
europepmc   +2 more sources

Binarized Neural Networks for Resource-Efficient Spike Sorting

IEEE Access
Deep learning is fastly gaining ground in neuroscience. In the field of implantable brain computer interfaces, a fundamental application of deep learning is to sort action potentials (known as spikes), measured with extracellular electrodes, according to
Luca M. Meyer, Majid Zamani, Andreas Demosthenous   +2 more
doaj   +2 more sources

An FPGA-Based Hardware/Software Design Using Binarized Neural Networks for Agricultural Applications: A Case Study

IEEE Access, 2021
This work presents an FPGA-based hardware/software design to help the agricultural robot intelligently decide if biological agents need to be applied to the target crops.
Chun-Hsian Huang
doaj   +2 more sources

Energy-Efficient Non-Von Neumann Computing Architecture Supporting Multiple Computing Paradigms for Logic and Binarized Neural Networks

Journal of Low Power Electronics and Applications, 2021
Different in-memory computing paradigms enabled by emerging non-volatile memory technologies are promising solutions for the development of ultra-low-power hardware for edge computing.
Tommaso Zanotti, Francesco Maria Puglisi, Paolo Pavan   +2 more
doaj   +2 more sources

Partially binarized neural networks for efficient spike sorting. [PDF]

Biomed Eng Lett, 2023
Valencia D, Alimohammad A.
europepmc   +2 more sources

Taming Binarized Neural Networks and Mixed-Integer Programs [PDF]

AAAI Conference on Artificial Intelligence, 2023
There has been a great deal of recent interest in binarized neural networks, especially because of their explainability. At the same time, automatic differentiation algorithms such as backpropagation fail for binarized neural networks, which limits their
Johannes Aspman, Georgios Korpas, Jakub Mareček   +2 more
semanticscholar   +1 more source