Training neural networks with fixed sparse masks

YL Sung, V Nair, CA Raffel - Advances in Neural …, 2021 - proceedings.neurips.cc
During typical gradient-based training of deep neural networks, all of the model's
parameters are updated at each iteration. Recent work has shown that it is possible to …
被引用次数：139 相关文章

Training Neural Networks with Fixed Sparse Masks

YL Sung, V Nair, C Raffel - arXiv preprint arXiv:2111.09839, 2021 - arxiv.org
During typical gradient-based training of deep neural networks, all of the model's
parameters are updated at each iteration. Recent work has shown that it is possible to …

Training neural networks with fixed sparse masks

YL Sung, V Nair, C Raffel - … of the 35th International Conference on …, 2021 - dl.acm.org
During typical gradient-based training of deep neural networks, all of the model's
parameters are updated at each iteration. Recent work has shown that it is possible to …

Training Neural Networks with Fixed Sparse Masks

YL Sung, V Nair, CA Raffel - Advances in Neural …, 2021 - proceedings.neurips.cc
During typical gradient-based training of deep neural networks, all of the model's
parameters are updated at each iteration. Recent work has shown that it is possible to …

Training Neural Networks with Fixed Sparse Masks

YL Sung, V Nair, C Raffel - arXiv e-prints, 2021 - ui.adsabs.harvard.edu
During typical gradient-based training of deep neural networks, all of the model's
parameters are updated at each iteration. Recent work has shown that it is possible to …

Training Neural Networks with Fixed Sparse Masks

YL Sung, V Nair, C Raffel - Advances in Neural Information Processing … - openreview.net
During typical gradient-based training of deep neural networks, all of the model's
parameters are updated at each iteration. Recent work has shown that it is possible to …