Expressive power of outer product manifolds on feed-forward neural networks

Autor:	Dar��czy, B��lint, Aleksziev, Rita, Bencz��r, Andr��s
Jazyk:	angličtina
Rok vydání:	2018
Předmět:	FOS: Computer and information sciences Computer Science - Machine Learning Statistics - Machine Learning Machine Learning (stat.ML) Machine Learning (cs.LG)
Popis:	Hierarchical neural networks are exponentially more efficient than their corresponding "shallow" counterpart with the same expressive power, but involve huge number of parameters and require tedious amounts of training. Our main idea is to mathematically understand and describe the hierarchical structure of feedforward neural networks by reparametrization invariant Riemannian metrics. By computing or approximating the tangent subspace, we better utilize the original network via sparse representations that enables switching to shallow networks after a very early training stage. Our experiments show that the proposed approximation of the metric improves and sometimes even surpasses the achievable performance of the original network significantly even after a few epochs of training the original feedforward network. 11 pages, 8 figures, under submission
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::64b0993ef5a6bfcd54872e984d4946b3 http://arxiv.org/abs/1807.06630 Zobrazit plný text záznamu