Specifying Weight Priors in Bayesian Deep Neural Networks with Empirical Bayes
نویسندگان
چکیده
منابع مشابه
Robust Bayes and Empirical Bayes Analysis with # -Contaminated Priors
Your use of the JSTOR archive indicates your acceptance of JSTOR's Terms and Conditions of Use, available at http://www.jstor.org/about/terms.html. JSTOR's Terms and Conditions of Use provides, in part, that unless you have obtained prior permission, you may not download an entire issue of a journal or multiple copies of articles, and you may use content in the JSTOR archive only for your perso...
متن کاملGraph Priors for Deep Neural Networks
In this work we explore how gene-gene interaction graphs can be used as a prior for the representation of a model to construct features based on known interactions between genes. Most existing machine learning work on graphs focuses on building models when data is confined to a graph structure. In this work we focus on using the information from a graph to build better representations in our mo...
متن کاملGradient conjugate priors and deep neural networks
The paper deals with learning the probability distribution of the observed data by artificial neural networks. We suggest a so-called gradient conjugate prior (GCP) update appropriate for neural networks, which is a modification of the classical Bayesian update for conjugate priors. We establish a connection between the gradient conjugate prior update and the maximization of the log-likelihood ...
متن کاملModel Selection in Bayesian Neural Networks via Horseshoe Priors
Bayesian Neural Networks (BNNs) have recently received increasing attention for their ability to provide well-calibrated posterior uncertainties. However, model selection—even choosing the number of nodes—remains an open question. In this work, we apply a horseshoe prior over node preactivations of a Bayesian neural network, which effectively turns off nodes that do not help explain the data. W...
متن کاملOn weight initialization in deep neural networks
A proper initialization of the weights in a neural network is critical to its convergence. Current insights into weight initialization come primarily from linear activation functions. In this paper, I develop a theory for weight initializations with non-linear activations. First, I derive a general weight initialization strategy for any neural network using activation functions differentiable a...
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: 2020
ISSN: 2374-3468,2159-5399
DOI: 10.1609/aaai.v34i04.5875