N. Siddharth

Learn More
We present a system that demonstrates how the compositional structure of events, in concert with the compositional structure of language, can interplay with the underlying focusing mechanisms in video action recognition, providing a medium for top-down and bottom-up integration as well as multi-modal integration between vision and language. We show how the(More)
A number of recent approaches to policy learning in 2D game domains have been successful going directly from raw input images to actions. However when employed in complex 3D environments, they typically suffer from challenges related to partial observability, combinatorial exploration spaces, path planning, and a scarcity of rewarding scenarios. Inspired(More)
We present an approach to simultaneously reasoning about a video clip and an entire natural-language sentence. The compositional nature of language is exploited to construct models which represent the meanings of entire sentences composed out of the meanings of the words in those sentences mediated by a grammar that encodes the predicate-argument relations.(More)
We present an approach to searching large video corpora for clips which depict a natural-language query in the form of a sentence. Compositional semantics is used to encode subtle meaning differences lost in other approaches, such as the difference between two sentences which have identical words but entirely different meaning: The person rode the horse(More)
Mammalian gastric lipases are stable and active under acidic conditions and also in the duodenal lumen. There has been considerable interest in acid stable lipases owing to their potential application in the treatment of pancreatic exocrine insufficiency. In order to gain insights into the domain movements of these enzymes, molecular dynamics simulations of(More)
Variational autoencoders (VAEs) learn representations of data by jointly training a probabilistic encoder and decoder network. Typically these models encode all features of the data into a single variable. Here we are interested in learning disentangled representations that encode distinct aspects of the data into separate variables. We propose to learn(More)
Deep generative models provide a powerful and flexible means to learn complex distributions over data by incorporating neural networks into latent-variable models. Variational approaches to training such models introduce a probabilistic encoder that casts data, typically unsupervised, into an entangled representation space. While unsupervised learning is(More)
Many practical techniques for probabilistic inference require a sequence of distributions that interpolate between a tractable distribution and an intractable distribution of interest. Usually, the sequences used are simple, e.g., based on geometric averages between distributions. When models are expressed as probabilistic programs, the models themselves(More)
In this paper we describe a system that performs software installation on a vast heterogeneous network using mobile agents. More specifically, the Java aglets platform has been used to achieve this purpose. We require that a one time installation of the Java aglet server is done on all nodes in the network. When new software is to be installed, the central(More)