Artificial Intelligence
Building intelligent machines that complement human reasoning and extend what people can do.
Video
Counterfactual Fairness
Machine learning can impact people with legal or ethical consequences when it is used to automate decisions in areas such as insurance, lending, hiring, and predictive policing. In many of these scenarios, previous decisions have…
Video
Variational Continual Learning
This talk introduces variational continual learning, a simple but general framework for continual learning that fuses online variational inference (VI) and recent advances in Monte Carlo VI for neural networks. The framework can successfully train…
Video
Distill and transfer learning for robust multitask RL
Most deep reinforcement learning algorithms are data inefficient in complex and rich environments, limiting their applicability to many scenarios. One direction for improving data efficiency is multitask learning with shared neural network parameters, where efficiency…
Video
Priors for Deep Networks: Limit theorems, pitfalls, open questions
Much research in Bayesian Deep Learning is about approximating the posterior. With some notable exceptions, the choice of prior is less often considered. In this second direction, we discuss recent work on central limit theorems…
Video
Active Mini-Batch Sampling using Repulsive Point Processes
The performance of stochastic gradient descent (SGD) can be improved by actively selecting mini-batches. In this work, we explore active mini-batch selection using repulsive point processes. This simultaneously introduces active bias and leads to stochastic…
Video
Reconciling Cancer Genotype and Phenotypes by Learning Structured Priors
Cancer is often viewed as a genetic disease because accumulation of mutations in the DNA are said to “drive” the progression of the disease. Depending on the mutations, an individual may exhibit some or many…
Video
Temporal Difference Models: Deep Model-free RL for Model-based
Deep reinforcement learning (RL) has shown promising results for learning complex sequential decision-making behaviors in various environments. However, most successes have been exclusively in simulation, and results in real-world applications such as robotics are limited,…
Video
Debiasing Evidence Approximations: On Importance-Weighted Autoencoders and Jackknife Variational Inference
The importance-weighted autoencoder (IWAE) approach of Burda et al. (2015) defines a sequence of increasingly tighter bounds on the marginal likelihood of latent variable models. Recently, Cremer et al. (2017) reinterpreted the IWAE bounds as…
Video
Graph neural networks: Variations and applications
Many real-world tasks require understanding interactions between a set of entities. Examples include interacting atoms in chemical molecules, people in social networks and even syntactic interactions between tokens in program source code. Graph structured data…
