Karl Ridgeway

A Survey of Inductive Biases for Factorial Representation-Learning

2016 · arXiv (Cornell University)

With the resurgence of interest in neural networks, representation learning has re-emerged as a central focus in artificial intelligence. Representation learning refers to the discovery of useful encodings of data that make domain-relevant information explicit. …

Open-Ended Content-Style Recombination Via Leakage Filtering

2018 · arXiv (Cornell University)

We consider visual domains in which a class label specifies the content of an image, and class-irrelevant properties that differentiate instances constitute the style. We present a domain-independent method that permits the open-ended recombination of …