YoVDO

Deconstructing Lottery Tickets - Zeros, Signs, and the Supermask

Offered By: Yannic Kilcher via YouTube

Tags

Deep Learning Courses Neural Networks Courses Model Optimization Courses

Course Description

Overview

Explore the intricacies of the Lottery Ticket Hypothesis in this in-depth video analysis. Delve into the paper "Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask" to uncover key insights about creating sparse networks. Learn why setting weights to zero is crucial, how signs alone can enable reinitialized network training, and the relationship between masking and training. Discover the concept of Supermasks and their potential to significantly improve performance in untrained, randomly initialized networks. Gain a deeper understanding of neural network sparsity, weight initialization, and the factors contributing to the success of Lottery Ticket networks.

Syllabus

Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask (Paper Explained)


Taught by

Yannic Kilcher

Related Courses

Neural Networks for Machine Learning
University of Toronto via Coursera
Good Brain, Bad Brain: Basics
University of Birmingham via FutureLearn
Statistical Learning with R
Stanford University via edX
Machine Learning 1—Supervised Learning
Brown University via Udacity
Fundamentals of Neuroscience, Part 2: Neurons and Networks
Harvard University via edX