Follow
Critical initialization of wide and deep neural networks through partial Jacobians: general theory and applications to LayerNorm. (arXiv:2111.12143v1 [cs.LG]) http://arxiv.org/abs/2111.12143
Critical initialization of wide and deep neural networks through partial Jacobians: general theory and applications to LayerNorm. (arXiv:2111.12143v1 [cs.LG]) http://arxiv.org/abs/2111.12143