Holomorphic equilibrium propagation computes exact gradients through finite size oscillations
A Laborieux, F Zenke - Advances in neural information …, 2022 - proceedings.neurips.cc
Equilibrium propagation (EP) is an alternative to backpropagation (BP) that allows the
training of deep neural networks with local learning rules. It thus provides a compelling …
training of deep neural networks with local learning rules. It thus provides a compelling …
Holomorphic Equilibrium Propagation Computes Exact Gradients Through Finite Size Oscillations
A Laborieux, F Zenke - Advances in Neural Information Processing …, 2022 - openreview.net
Equilibrium propagation (EP) is an alternative to backpropagation (BP) that allows the
training of deep neural networks with local learning rules. It thus provides a compelling …
training of deep neural networks with local learning rules. It thus provides a compelling …
Holomorphic equilibrium propagation computes exact gradients through finite size oscillations
A Laborieux, F Zenke - Proceedings of the 36th International Conference …, 2022 - dl.acm.org
Equilibrium propagation (EP) is an alternative to backpropagation (BP) that allows the
training of deep neural networks with local learning rules. It thus provides a compelling …
training of deep neural networks with local learning rules. It thus provides a compelling …
Holomorphic Equilibrium Propagation Computes Exact Gradients Through Finite Size Oscillations
A Laborieux, F Zenke - arXiv e-prints, 2022 - ui.adsabs.harvard.edu
Equilibrium propagation (EP) is an alternative to backpropagation (BP) that allows the
training of deep neural networks with local learning rules. It thus provides a compelling …
training of deep neural networks with local learning rules. It thus provides a compelling …
Holomorphic Equilibrium Propagation Computes Exact Gradients Through Finite Size Oscillations
A Laborieux, F Zenke - arXiv preprint arXiv:2209.00530, 2022 - arxiv.org
Equilibrium propagation (EP) is an alternative to backpropagation (BP) that allows the
training of deep neural networks with local learning rules. It thus provides a compelling …
training of deep neural networks with local learning rules. It thus provides a compelling …
[引用][C] Holomorphic equilibrium propagation computes exact gradients through finite size oscillations
A Laborieux - laborieux-axel.github.io
In this work we investigate an interesting and previously unexplored link between the
optimization process of binarized neural networks (BNNs) and neuroscience theories of …
optimization process of binarized neural networks (BNNs) and neuroscience theories of …