Praniti Ram Patil

Fixed-point theorems in training deep neural networks

Praniti Ram Patil, Suresh Singh Rajpurohit, Manthan Joshi, Harsha Dave, Aakash Mansaram Gojare, Ashwini Prasad Parkar

In this paper: This paper discuss fixed-point theories can be used to train deep neural networks. We find a mathematical link between nonlinear analysis and learning dynamics by looking at neural network optimisatio...