Results 11 to 20 of about 22,800 (222)
ReBNet: Residual Binarized Neural Network [PDF]
2018 IEEE 26th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), 2018 This paper proposes ReBNet, an end-to-end framework for training reconfigurable binary neural networks on software and developing efficient accelerators for execution on FPGA.
Ghasemzadeh, Mohammad +2 more
core +2 more sources
Verifying Properties of Binarized Deep Neural Networks
Proceedings of the AAAI Conference on Artificial Intelligence, 2018 Understanding properties of deep neural networks is an important challenge in deep learning. In this paper, we take a step in this direction by proposing a rigorous way of verifying properties of a popular class of neural networks, Binarized Neural ...
Kasiviswanathan, Shiva Prasad +4 more
core +3 more sources
Binarized graph neural network [PDF]
World Wide Web, 2021 Recently, there have been some breakthroughs in graph analysis by applying the graph neural networks (GNNs) following a neighborhood aggregation scheme, which demonstrate outstanding performance in many tasks. However, we observe that the parameters of the network and the embedding of nodes are represented in real-valued matrices in existing GNN-based ...
Hanchen Wang +6 more
openaire +2 more sources
Synaptic metaplasticity in binarized neural networks [PDF]
Nature Communications, 2021 AbstractWhile deep neural networks have surpassed human performance in multiple situations, they are prone to catastrophic forgetting: upon training a new task, they rapidly forget previously learned ones. Neuroscience studies, based on idealized tasks, suggest that in the brain, synapses overcome this issue by adjusting their plasticity depending on ...
Axel Laborieux +3 more
openaire +5 more sources
Neural Spike Sorting Using Binarized Neural Networks [PDF]
IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2021 This article presents the design and efficient hardware implementation of binarized neural networks (BNNs) for brain-implantable neural spike sorting. In contrast to the conventional artificial neural networks (ANNs), in which the weights and activation functions of neurons are represented using real values, the BNNs utilize binarized weights and ...
Daniel Valencia, Amir Alimohammad
openaire +2 more sources
Bimodal-Distributed Binarized Neural Networks
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-precision counterparts.
Tal Rozen +4 more
openaire +3 more sources
A storage-efficient ensemble classification using filter sharing on binarized convolutional neural networks [PDF]
PeerJ Computer Science, 2022 This paper proposes a storage-efficient ensemble classification to overcome the low inference accuracy of binary neural networks (BNNs). When external power is enough in a dynamic powered system, classification results can be enhanced by aggregating ...
HyunJin Kim +2 more
doaj +2 more sources
A Binarized Neural Network Approach to Accelerate in-Vehicle Network Intrusion Detection
IEEE Access, 2022 Controller Area Network (CAN) is the de facto standard for in-vehicle networks. However, it is inherently vulnerable to various attacks due to the lack of security features.
Linxi Zhang, Xuke Yan, Di Ma
doaj +1 more source
Elastic-Link for Binarized Neural Networks
Proceedings of the AAAI Conference on Artificial Intelligence, 2022 Recent work has shown that Binarized Neural Networks (BNNs) are able to greatly reduce computational costs and memory footprints, facilitating model deployment on resource-constrained devices. However, in comparison to their full-precision counterparts, BNNs suffer from severe accuracy degradation.
Hu, Jie +5 more
openaire +2 more sources
An Adiabatic Method to Train Binarized Artificial Neural Networks [PDF]
Scientific Reports, 2021 Abstract An artificial neural network consists of neurons and synapses. Neuron gives output based on its input according to non-linear activation functions such as the Sigmoid, Hyperbolic Tangent (Tanh), or Rectified Linear Unit (reLU) functions, etc. Synapses connect the neuron outputs to their inputs with tunable real-valued weights. The most
Yuansheng Zhao, Jiang Xiao
openaire +4 more sources