YoVDO

Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers

Offered By: Simons Institute via YouTube

Tags

Deep Learning Courses Gradient Descent Courses Semi-supervised Learning Courses

Course Description

Overview

Explore the concept of provably robust deep learning through adversarially trained smoothed classifiers in this 47-minute lecture by Jerry Li from Microsoft Research. Delve into key topics including randomization, the Zico idea, experimental results, semi-supervised learning, training techniques, notation, gradients, and the optimal gradient. Examine the full algorithm, its parameters, and the resulting outcomes. Gain insights into the frontiers of deep learning and the development of more resilient neural networks.

Syllabus

Intro
Definition
Randomization
Zico
Idea
Experimental Results
SemiSupervised Results
Training
Notation
Gradients
Optimal Gradient
Full Algorithm
Parameters
Results
Summary


Taught by

Simons Institute

Related Courses

Practical Predictive Analytics: Models and Methods
University of Washington via Coursera
Deep Learning Fundamentals with Keras
IBM via edX
Introduction to Machine Learning
Duke University via Coursera
Intro to Deep Learning with PyTorch
Facebook via Udacity
Introduction to Machine Learning for Coders!
fast.ai via Independent