Results 61 to 70 of about 1,721,209 (309)

Spectral neural network potentials for binary alloys [PDF]

Journal of Applied Physics, 2020
In this work, we present a numerical implementation to compute the atom-centered descriptors introduced by Bartok et al. [Phys. Rev. B 87, 184115 (2013)] based on the harmonic analysis of the atomic neighbor density function. Specifically, we focus on two types of descriptors, the smooth SO(3) power spectrum with the explicit inclusion of a radial ...
David Zagaceta, Howard Yanxon, Qiang Zhu
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 ...
Tal Rozen, Moshe Kimhi, Brian Chmiel, Avi Mendelson, Chaim Baskin   +4 more
doaj   +1 more source

Hyperbolic Binary Neural Network

IEEE Transactions on Neural Networks and Learning Systems
Binary Neural Network (BNN) converts full-precision weights and activations into their extreme 1-bit counterparts, making it particularly suitable for deployment on lightweight mobile devices. While binary neural networks are typically formulated as a constrained optimization problem and optimized in the binarized space, general neural networks are ...
Jun Chen, Jingyang Xiang, Tianxin Huang, Xiangrui Zhao, Yong Liu   +4 more
openaire   +3 more sources

Controlling information capacity of binary neural network [PDF]

Pattern Recognition Letters, 2020
Despite the growing popularity of deep learning technologies, high memory requirements and power consumption are essentially limiting their application in mobile and IoT areas. While binary convolutional networks can alleviate these problems, the limited bitwidth of weights is often leading to significant degradation of prediction accuracy.
Dmitry Ignatov, Andrey Ignatov
openaire   +2 more sources

Uncertainty-Aware Deep Learning Methods for Robust Diabetic Retinopathy Classification

IEEE Access, 2022
Automatic classification of diabetic retinopathy from retinal images has been increasingly studied using deep neural networks with impressive results.
Joel Jaskari, Jaakko Sahlsten, Theodoros Damoulas, Jeremias Knoblauch, Simo Sarkka, Leo Karkkainen, Kustaa Hietala, Kimmo K. Kaski   +7 more
doaj   +1 more source

Neural Networks Architecture Evaluation in a Quantum Computer

, 2017
In this work, we propose a quantum algorithm to evaluate neural networks architectures named Quantum Neural Network Architecture Evaluation (QNNAE). The proposed algorithm is based on a quantum associative memory and the learning algorithm for artificial
da Silva, Adenilton José, de Oliveira, Rodolfo Luan F.   +1 more
core   +1 more source

Vehicle classification algorithm based on binary proximity sensors and neural networks

Tongxin xuebao, 2008
To improve the classification accuracy, a new algorithm was developed with binary proximity magnetic sen- sors and back propagation neural networks. In this algorithm, use the low cost and high sensitive magnetic sensors to de- tect the magnetic field ...
ZHANG Wei, TAN Guo-zhen, DING Nan, SHANG Yao   +3 more
doaj   +2 more sources

Recurrent Residual Networks Contain Stronger Lottery Tickets

IEEE Access, 2023
Accurate neural networks can be found just by pruning a randomly initialized overparameterized model, leaving out the need for any weight optimization.
Angel Lopez Garcia-Arias, Yasuyuki Okoshi, Masanori Hashimoto, Masato Motomura, Jaehoon Yu   +4 more
doaj   +1 more source

A Digital Neuromorphic Architecture Efficiently Facilitating Complex Synaptic Response Functions Applied to Liquid State Machines

, 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., Carlson, Kristofor D., Donaldson, Jonathon, Follett, David R., Follett, Pamela L., Hill, Aaron J., James, Conrad D., Naegle, John H., Smith, Michael R., Vineyard, Craig M.   +9 more
core   +1 more source

Noise-optimal binary-synapse neural networks

Journal of Physics A: Mathematical and General, 1993
The authors examine the possibility of improving the performance of discrete-synapse neural networks, functioning as content-addressable memories, by the inclusion of noise in their training procedure, and study the effects on the training itself.
Penney, R, Sherrington, D
openaire   +1 more source