منابع مشابه
Fast Power system security analysis with Guided Dropout
We propose a new method to efficiently compute load-flows (the steady-state of the power-grid for given productions, consumptions and grid topology), substituting conventional simulators based on differential equation solvers. We use a deep feed-forward neural network trained with load-flows precomputed by simulation. Our architecture permits to train a network on so-called “n-1” problems, in w...
متن کاملUnderstanding Dropout
Dropout is a relatively new algorithm for training neural networks which relies on stochastically “dropping out” neurons during training in order to avoid the co-adaptation of feature detectors. We introduce a general formalism for studying dropout on either units or connections, with arbitrary probability values, and use it to analyze the averaging and regularizing properties of dropout in bot...
متن کاملConcrete Dropout
• Gal and Gharamani (2015) reinterpreted dropout regularisation as approximate inference in BNNs •Dropout probabilities pl are variational parameters of the approximate posterior qθ(ω) = ∏ k qMk,pk(Wk), where Wk = Mk · diag (zk) and zkl iid ∼Bernoulli(1− pk) • Concrete distribution (Maddison et al., Jang et al.) relaxes Categorical distribution to obtain gradients wrt the probability vector – E...
متن کاملFraternal Dropout
Recurrent neural networks (RNNs) form an important class of architectures among neural networks useful for language modeling and sequential prediction. However, optimizing RNNs is known to be harder compared to feed-forward neural networks. A number of techniques have been proposed in literature to address this problem. In this paper we propose a simple technique called fraternal dropout that t...
متن کاملDropout distillation
Dropout is a popular stochastic regularization technique for deep neural networks that works by randomly dropping (i.e. zeroing) units from the network during training. This randomization process allows to implicitly train an ensemble of exponentially many networks sharing the same parametrization, which should be averaged at test time to deliver the final prediction. A typical workaround for t...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Proceedings of the AAAI Conference on Artificial Intelligence
سال: 2019
ISSN: 2374-3468,2159-5399
DOI: 10.1609/aaai.v33i01.33014065