Slides

Introduction

I talk about the course, and what we'll be doing this semester.

Densities 101

I talk about densities, sampling, and estimation.

Project Runway

I talk about possible projects.

Nonparametric Statistics

I talk about nonparametric methods and learning over distributions.

Kernels & Random Features

Introduction and motivation of Mercer Kernels.

MMD & Two Sample Testing

Kernels for comparing and representing distributions.

Sequential Modeling

Word Embeddings

Language Modeling

Generative Modeling I

Overview, autoregressive conditionals, and transformation of variable (flow) models.

Generative Modeling II

GANs, VAEs, and applications.

Multitask/Transfer Learning

How can we utilize related problems for better learning or generalization?

zero/One/Few-Shot Learning

How can we utilize class side-information for better generalization?

Differentiable Computing

Differentiable memory operations in ML models.

Graph Neural Networks

Discriminative and generative architectures for graph data.

Dimensionality Reduction

Multi-modal Data

Multi-modal Data II

Intro to RL

RL II & Imitation Learning

Spotlights