Earlier this month, Alec Radford — indico’s Head of Research — led a talk at Boston ML Forum. He presented an overview of recent work in generative modeling, including research that he, Luke Metz, and Soumith Chintala (FAIR) released in November 2015: Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. Video and slides below.


In recent years, deep learning approaches have come to dominate discriminative problems in many sub-areas of machine learning. Alongside this, they have also powered exciting improvements in generative and conditional modeling of richly structured data such as text, images, and audio. This talk serves as an introduction to several emerging application areas of generative modeling and provides a survey of recent techniques in the field.


Suggested Posts

The Good, Bad, & Ugly of TensorFlow

Regressor Based Image Stylization

Deep Learning in Fashion (Part 3): Clothing Matching Tutorial