Convergence Results for Neural Networks via Electrodynamics

conference on innovations in theoretical computer science, pp. 22:1-22:19, 2018.

Cited by: 13|Bibtex|Views44|
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com

Abstract:

We study whether a two neural network can learn another depth two network using gradient descent. Assuming a linear output node, we show that the question of whether gradient descent converges to the target function is equivalent to the following question in electrodynamics: Given k fixed protons in R^d, and k electrons, each moving due ...More

Code:

Data:

Your rating :
0

 

Tags
Comments