minima
このタグの解説について
この解説文は、すでに終了したサービス「はてなキーワード」内で有志のユーザーが作成・編集した内容に基づいています。その正確性や網羅性をはてなが保証するものではありません。問題のある記述を発見した場合には、お問い合わせフォームよりご連絡ください。関連ブログ
ネットで話題
もっと見る15ブックマークDeep Learning without Poor Local MinimaIn this paper, we prove a conjecture published in 1989 and also partially address an open problem announced at the Conference on Learning Theory (COLT) 2015. With no unrealistic assumption, we first prove the following statements for the squared loss function of deep linear neural networks with a...
arxiv.org
arxiv.org
www.switch-science.com7ブックマークOn Large-Batch Training for Deep Learning: Generalization Gap and Sharp MinimaThe stochastic gradient descent (SGD) method and its variants are algorithms of choice for many Deep Learning tasks. These methods operate in a small-batch regime wherein a fraction of the training data, say $32$-$512$ data points, is sampled to compute an approximation to the gradient. It has be...
arxiv.org
arxiv.org6ブックマークDepth Creates No Bad Local MinimaIn deep learning, \textit{depth}, as well as \textit{nonlinearity}, create non-convex loss surfaces. Then, does depth alone create bad local minima? In this paper, we prove that without nonlinearity, depth alone does not create bad local minima, although it induces non-convex loss surface. Using ...
arxiv.org
arxiv.org
qiita.com
blog-e.uosoft.net
www.meg2.net
nobulabo.com