Explore intriguing properties of neural networks in this 29-minute lecture from the University of Central Florida. Delve into key concepts including adversarial attacks, transfer learning, training overlap, and spectral analysis of instability. Examine semantic information in neural network units and identify potential weaknesses in these systems. Gain a deeper understanding of neural network behavior and challenges through this comprehensive overview of their fascinating characteristics.
Overview
Syllabus
Intro
Terminology
Intriguing properties
adversarial attack
transfer
training overlap
spectral analysis of unstability
Semantic information in units
Weaknesses
Taught by
UCF CRCV
Tags
Related Courses
-
Explaining and Harnessing Adversarial Examples in Machine Learning - Spring 2021
-
Trust Region Based Adversarial Attack on Neural Networks
-
Getting Robust - Securing Neural Networks Against Adversarial Attacks
-
Evaluating Neural Network Robustness - Targeted Attacks and Defenses
-
Neural Nets for NLP 2021 - Adversarial Methods
-
Neural Nets for NLP 2017 - Adversarial Learning
