Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Dar��czy, B��lint"'
Autor:
Dar��czy, B��lint
Recent articles indicate that deep neural networks are efficient models for various learning problems. However they are often highly sensitive to various changes that cannot be detected by an independent observer. As our understanding of deep neural
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d4e33f2c81cbef1d1bdf41f9c1f81808
http://arxiv.org/abs/2006.06780
http://arxiv.org/abs/2006.06780
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. By approximating the tangent s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::64535fc0fe3d3988cc612c6b91c2f91e
http://arxiv.org/abs/1912.09306
http://arxiv.org/abs/1912.09306
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 mathematic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::64b0993ef5a6bfcd54872e984d4946b3
http://arxiv.org/abs/1807.06630
http://arxiv.org/abs/1807.06630