PURPOSE Respiratory symptoms are the most common presenting complaint in primary
care. Often these symptoms are self resolving, but they can indicate a severe illness. With …

Clinical Text Notes (CTNs) contain physicians' reasoning process, written in an unstructured
free text format, as they examine and interview patients. In recent years, several studies …

In this paper, we propose a new experimental protocol and use it to benchmark the data
efficiency --- performance as a function of training set size --- of two deep learning algorithms, …

We propose Power Slow Feature Analysis, a gradient-based method to extract temporally
slow features from a high-dimensional input stream that varies on a faster time-scale, as a …

… It is generally not true that the distance function d and all … d were computable, using it naïvely
can bring about its own problems as was alluded to above. We argue that instead of using d …

Several methods of estimating the mutual information of random variables have been developed
in recent years. They can prove valuable for novel approaches to learning statistically …

… in a supervised fashion from a data set of observed transitions, D = {(st,at,rt,st+1)i}. The
world models can be used in multiple different ways, depending on the algorithm, to derive the …

Prediction variance on unseen data harms the generalization performance of deep neural
network classifiers. We assess the utility of forming ensembles of deep neural networks in the …

Planning in high-dimensional space remains a challenging problem, even with recent advances
in algorithms and computational power. We are inspired by efference copy and sensory …

Clinical Text Notes (CTNs) contain physicians’ reasoning process, written in an unstructured
free text format, as they examine and interview patients. In recent years, several studies …