281 citations · 819 across the 24 of their papers we have counts for
24 papers
Memorization in Deep Neural Networks: Does the Loss Function matter?
Deep Patel, P. S. Sastry
Deep Neural Networks, often owing to the overparameterization, are shown to be capable of exactly memorizing even randomly labelled data. Empirical studies have also shown that non…
Adaptive Sample Selection for Robust Learning under Label Noise
Deep Patel, P. S. Sastry
Deep Neural Networks (DNNs) have been shown to be susceptible to memorization or overfitting in the presence of noisily-labelled data. For the problem of robust learning under such…
Learning Gaussian-Bernoulli RBMs using Difference of Convex Functions Optimization
Vidyadhar Upadhya, P S Sastry
The Gaussian-Bernoulli restricted Boltzmann machine (GB-RBM) is a useful generative model that captures meaningful features from the given -dimensional continuous data. The diff…
PLUME: Polyhedral Learning Using Mixture of Experts
Kulin Shah, P. S. Sastry, Naresh Manwani
In this paper, we propose a novel mixture of expert architecture for learning polyhedral classifiers. We learn the parameters of the classifierusing an expectation maximization alg…
Summarizing Event Sequences with Serial Episodes: A Statistical Model and an Application
Soumyajit Mitra, P S Sastry
In this paper we address the problem of discovering a small set of frequent serial episodes from sequential data so as to adequately characterize or summarize the data. We discuss…
Efficient Learning of Restricted Boltzmann Machines Using Covariance Estimates
Vidyadhar Upadhya, P. S. Sastry
Learning RBMs using standard algorithms such as CD(k) involves gradient descent on the negative log-likelihood. One of the terms in the gradient, which involves expectation w.r.t.…