Lecture 1 | Introduction to Convolutional Neural Networks for Visual Recognition
57:56Lecture 2 | Image Classification
59:31Lecture 3 | Loss Functions and Optimization
1:14:40Lecture 4 | Introduction to Neural Networks
1:13:59Lecture 5 | Convolutional Neural Networks
1:08:56Lecture 6 | Training Neural Networks I
1:20:19Lecture 7 | Training Neural Networks II
1:15:30Lecture 8 | Deep Learning Software
1:18:07Lecture 9: CNN Architectures (CS231n)
1:17:40Lecture 10: Recurrent Neural Networks (CS231n)
1:13:09Lecture 11: Detection and Segmentation (CS231n)
1:14:26Lecture 12: Visualizing and Understanding (CS231n)
1:15:48Lecture 13: Generative Models (CS231n)
1:17:41Lecture 14: Deep Reinforcement Learning (CS231n)
1:04:01Lecture 15: Efficient Methods and Hardware for Deep Learning (CS231n)
1:16:52Lecture 16: Adversarial Examples and Adversarial Training (CS231n)
1:21:46Lecture 16: Adversarial Examples and Adversarial Training (CS231n)
Guest lecturer Ian Goodfellow explains the phenomenon of adversarial examples in deep learning and their exploitation in attacking machine learning systems. The lecture explores defense strategies and the utility of adversarial training to enhance model robustness.
In Lecture 16, guest lecturer Ian Goodfellow discusses adversarial examples in deep learning. We discuss why deep networks and other machine learning models are susceptible to adversarial examples, and how adversarial examples can be used to attack machine learning systems. We discuss potential defenses against adversarial examples, and uses for adversarial examples for improving machine learning systems even without an explicit adversary.
Keywords: Adversarial examples, Fooling images, fast gradient sign method, Clever Hans, adversarial defenses, adversarial examples in the physical world, adversarial training, virtual adversarial training, model-based optimization