Art with MI Demo: Adversarially learned inference – with Aaron Courville

Aaron Courville (University of Montreal) discusses deep generative directed models and explores two main techniques currently used: Variational Auto-Encoders (VAE) and Generative Adversarial Networks (GAN). This talk was recorded at the Music, Art & Machine Intelligence 2016 workshop in San Francisco.

Visual Reasoning via Feature-wise Linear Modulation- Aaron Courville

Visual Reasoning - answering image-related questions which require a multi-step process to answer - is a task that explores how well models can learn about complex organizational structure of objects in the world.

SANE2017: Aaron Courville: Progress on the Road to End-to-End Speech Synthesis

Professor Aaron Courville of the University of Montreal describes recent work on deep learning for speech synthesis. At Speech and Audio in the North East Workshop SANE 2017, Google, New York, 2017-10-19

MIT 6.S191 (2018): Deep Generative Modeling

MIT Introduction to Deep Learning 6.S191: Lecture 4 Deep Generative Modeling Lecturer: Aaron Courville January 2018