Deep Learning Limitations and New Frontiers

Overview

This course explores the limitations and new frontiers of deep learning. The learning outcomes include understanding the challenges faced by deep learning models and exploring new research directions in the field. The course covers topics such as adversarial attacks on neural networks, Bayesian deep learning for uncertainty, and model uncertainty applications. The teaching method includes lectures, slides, and lab materials. The course is intended for individuals interested in deep learning, neural networks, and the future of artificial intelligence.

Syllabus

Intro
T-shirts!
Final Class Project
Thursday: Deep Learning in Industry
Friday: Project Presentations
Power of Neural Nets
History of Artificial Intelligence Hype
Rethinking Generalization
Capacity of Deep Neural Networks
Function Approximators
Adversarial Attacks on Neural Networks
Neural Network Limitations...
Why Care About Uncertainty?
Bayesian Deep Learning for Uncertainty
Elementwise Dropout for Uncertainty
Model Uncertainty Application
Motivation
Model Controller
The Child Network
Learning to Learn: A level deeper
This Spawns a Very Powerful Idea