Online Program Home
My Program

Abstract Details

Activity Number: 2 - Introductory Overview Lecture: The Deep Learning Revolution
Type: Invited
Date/Time: Sunday, July 29, 2018 : 2:00 PM to 3:50 PM
Sponsor: JSM Partner Societies
Abstract #333054 Presentation 1 Presentation 2
Title: A Four-Part Introduction to Deep Learning
Author(s): Christopher Manning* and Ruslan Salakhutdinov*
Companies: Carnegie Mellon University and Stanford University
Keywords: neural networks; deep learning; representation learning; generative adversarial networks; vision; language

We introduce to the JSM community the mathematical and conceptual basics of recent deep learning methods, emphasizing the predictive power of multi-layer neural net models that learn distributed representations. Part 1 introduces neural nets, their supervised training by stochastic gradient descent (SGD) and back-propagation, and their big successes. Part 2 focuses on (non-convex) optimization, regularization, debugging and interpretation. Part 3 examines unsupervised learning, covering Boltzmann machines, variational autoencoders (VAEs), and particularly generative adversarial networks (GANs). Part 4 looks at applications to computer vision and human language, including object recognition, information retrieval, question answering, and machine translation, introducing convolutional nets, recurrent sequence models (LSTMs), and attention. Throughout, we try to make connections: Which neural net models can be cast as statistical models? Should statisticians now be using deep learning? Is this black-box really so easy to use, and, moreover, can it be opened? Where is there room for statisticians to contribute to the understanding of and further development of deep learning models?

Authors who are presenting talks have a * after their name.

Back to the full JSM 2018 program