Piecewise linear activations substantially shape the loss surfaces of
neural networks

Piecewise linear activations substantially shape the loss surfaces of neural networks

27 March 2020

Papers citing "Piecewise linear activations substantially shape the loss surfaces of neural networks"

10 / 10 papers shown

Title
Loss Landscape of Shallow ReLU-like Neural Networks: Stationary Points, Saddle Escape, and Network Embedding Zhengqing Wu Berfin Simsek Francois Ged ODL 40 0 0 08 Feb 2024
Non-convergence to global minimizers for Adam and stochastic gradient descent optimization and constructions of local minimizers in the training of artificial neural networks Arnulf Jentzen Adrian Riekert 38 4 0 07 Feb 2024
VacciNet: Towards a Smart Framework for Learning the Distribution Chain Optimization of Vaccines for a Pandemic Jayeeta Mondal Jeet Dutta H. Barua OffRL 19 0 0 01 Aug 2022
Why Quantization Improves Generalization: NTK of Binary Weight Neural Networks Kaiqi Zhang Ming Yin Yu-Xiang Wang MQ 16 4 0 13 Jun 2022
Modeling Image Composition for Complex Scene Generation Zuopeng Yang Daqing Liu Chaoyue Wang J. Yang Dacheng Tao ViT 34 50 0 02 Jun 2022
Exact Solutions of a Deep Linear Network Liu Ziyin Botao Li Xiangmin Meng ODL 19 21 0 10 Feb 2022
Non-attracting Regions of Local Minima in Deep and Wide Neural Networks Henning Petzka C. Sminchisescu 25 9 0 16 Dec 2018
Global optimality conditions for deep neural networks Chulhee Yun S. Sra Ali Jadbabaie 121 117 0 08 Jul 2017
A Survey on Deep Learning in Medical Image Analysis G. Litjens Thijs Kooi B. Bejnordi A. Setio F. Ciompi Mohsen Ghafoorian Jeroen van der Laak Bram van Ginneken C. I. Sánchez OOD 283 10,613 0 19 Feb 2017
The Loss Surfaces of Multilayer Networks A. Choromańska Mikael Henaff Michaël Mathieu Gerard Ben Arous Yann LeCun ODL 179 1,185 0 30 Nov 2014