A standard screening procedure involves video endoscopy of the Gastrointestinal tract. It is a
less invasive method which is practiced for early diagnosis of gastric diseases. Manual …

This thesis develops a method for automatically constructing, visualizing and describing a
large class of models, useful for forecasting and finding structure in domains such as time …

Machine learning potentials (MLPs) developed from extensive datasets constructed from
density functional theory calculations have become increasingly appealing to many …

We propose to study equivariance in deep neural networks through parameter symmetries.
In particular, given a group G that acts discretely on the input and output of a standard neural …

The chief difficulty in object recognition is that objects' classes are obscured by a large
number of extraneous sources of variability, such as pose and part deformation. These …

The use of kernel functions is a common technique to extract important features from
datasets. A quantum computer can be used to estimate kernel entries as transition …

Humans understand novel sentences by composing meanings and roles of core language
components. In contrast, neural network models for natural language modeling fail when …

We present a practical way of introducing convolutional structure into Gaussian processes,
making them more suited to high-dimensional inputs like images. The main contribution of …

Deep networks provide state-of-the-art performance in multiple imaging inverse problems
ranging from medical imaging to computational photography. However, most existing …

Stationary stochastic processes (SPs) are a key component of many probabilistic models,
such as those for off-the-grid spatio-temporal data. They enable the statistical symmetry of …