Understanding the computational difficulty of a binary-weight perceptron and the advantage of input sparseness
Z Bi, C Zhou - Journal of Physics A: Mathematical and …, 2019 - iopscience.iop.org
Limited precision of synaptic weights is a key aspect of both biological and hardware
implementation of neural networks. To assign low-precise weights during learning is a non …
implementation of neural networks. To assign low-precise weights during learning is a non …
Understanding the computational difficulty of a binary-weight perceptron and the advantage of input sparseness
Z Bi, C Zhou - Journal of Physics A Mathematical General, 2020 - ui.adsabs.harvard.edu
Limited precision of synaptic weights is a key aspect of both biological and hardware
implementation of neural networks. To assign low-precise weights during learning is a non …
implementation of neural networks. To assign low-precise weights during learning is a non …
Understanding the computational difficulty of a binary-weight perceptron and the advantage of input sparseness
Z Bi, C Zhou - arXiv preprint arXiv:1901.10856, 2019 - arxiv.org
Limited precision of synaptic weights is a key aspect of both biological and hardware
implementation of neural networks. To assign low-precise weights during learning is a non …
implementation of neural networks. To assign low-precise weights during learning is a non …
Understanding the computational difficulty of a binary-weight perceptron and the advantage of input sparseness
Z Bi, C Zhou - Journal of Physics. A, Mathematical and Theoretical …, 2020 - inis.iaea.org
[en] Limited precision of synaptic weights is a key aspect of both biological and hardware
implementation of neural networks. To assign low-precise weights during learning is a non …
implementation of neural networks. To assign low-precise weights during learning is a non …