Advances in biological and medical technologies have been providing us explosive
volumes of biological and physiological data, such as medical images …

The success of machine learning algorithms generally depends on data representation, and
we hypothesize that this is because different representations can entangle and hide more or …

Energy based models (EBMs) are appealing due to their generality and simplicity in
likelihood modeling, but have been traditionally difficult to train. We present techniques to …

We design a predictive layer for structured-output prediction (SOP) that can be plugged into
any neural network guaranteeing its predictions are consistent with a set of predefined …

Generating high-resolution, photo-realistic images has been a long-standing goal in
machine learning. Recently, Nguyen et al. 2016 showed one interesting way to synthesize …

An introduction to a broad range of topics in deep learning, covering mathematical and
conceptual background, deep learning techniques used in industry, and research …

Contrastive divergence is a popular method of training energy-based models, but is known
to have difficulties with training stability. We propose an adaptation to improve contrastive …

Deep learning algorithms seek to exploit the unknown structure in the input distribution in
order to discover good representations, often at multiple levels, with higher-level learned …

Deep learning research aims at discovering learning algorithms that discover multiple levels
of distributed representations, with higher levels representing more abstract concepts …

Controllable generation is one of the key requirements for successful adoption of deep
generative models in real-world applications, but it still remains as a great challenge. In …