no code implementations • 4 Mar 2018 • Harris Partaourides, Sotirios P. Chatzis
To alleviate this burden, in this paper we regard the DNN regularization problem from a Bayesian inference perspective: We impose a sparsity-inducing prior over the network synaptic weights, where the sparsity is induced by a set of Bernoulli-distributed binary variables with Beta (hyper-)priors over their prior parameters.
no code implementations • ICCV 2015 • Sotirios P. Chatzis
Unsupervised feature learning algorithms based on convolutional formulations of independent components analysis (ICA) have been demonstrated to yield state-of-the-art results in several action recognition benchmarks.
no code implementations • 14 Feb 2014 • Sotirios P. Chatzis
Based on this inspiration, in this paper we examine whether similar ideas from the field of Bayesian nonparametrics can be utilized in the context of modern DGMs in order to address the latent variable dimensionality inference problem.