Port-Hamiltonian Approach to Neural Network Training

Autor:	Massaroli, Stefano, Poli, Michael, Califano, Federico, Faragasso, Angela, Park, Jinkyoo, Yamashita, Atsushi, Asama, Hajime
Rok vydání:	2019
Předmět:	Computer Science - Neural and Evolutionary Computing Computer Science - Machine Learning Electrical Engineering and Systems Science - Systems and Control Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Neural networks are discrete entities: subdivided into discrete layers and parametrized by weights which are iteratively optimized via difference equations. Recent work proposes networks with layer outputs which are no longer quantized but are solutions of an ordinary differential equation (ODE); however, these networks are still optimized via discrete methods (e.g. gradient descent). In this paper, we explore a different direction: namely, we propose a novel framework for learning in which the parameters themselves are solutions of ODEs. By viewing the optimization process as the evolution of a port-Hamiltonian system, we can ensure convergence to a minimum of the objective function. Numerical experiments have been performed to show the validity and effectiveness of the proposed methods. Comment: To appear in the Proceedings of the 58th IEEE Conference on Decision and Control (CDC 2019). The first two authors contributed equally to the work
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1909.02702 Zobrazit plný text záznamu View this record from Arxiv