Reducing Neural Network Parameter Initialization Into an SMT Problem (Student Abstract)

Authors

  • Mohamad H. Danesh Oregon State Univeresity

Keywords:

Deep Neural Networks, Deep Learning, SMT Solver, Initialization

Abstract

Training a neural network (NN) depends on multiple factors, including but not limited to the initial weights. In this paper, we focus on initializing deep NN parameters such that it performs better, comparing to random or zero initialization. We do this by reducing the process of initialization into an SMT solver. Previous works consider certain activation functions on small NNs, however the studied NN is a deep network with different activation functions. Our experiments show that the proposed approach for parameter initialization achieves better performance comparing to randomly initialized networks.

Downloads

Published

2021-05-18

How to Cite

Danesh, M. H. (2021). Reducing Neural Network Parameter Initialization Into an SMT Problem (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 35(18), 15775-15776. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17884

Issue

Section

AAAI Student Abstract and Poster Program