For publicly viewable lecture recordings, see this playlist. This link is not intended for students taking the course. Students enrolled in CS182 should instead use the internal class playlist link.

Discussions

The discussion sections will not cover new material, but rather will give you additional practice solving problems. You can attend any discussion section you like. However, if there are less crowded sections that fit your schedule, those offer more opportunities for you to interact with your TA. See Syllabus for more information.

• Discussion 1: Introduction & Logistics. (solution)
• Discussion 2: Matrix Calc & Optimization. (solution)
• Discussion 3: Backpropagation & CNNs. (solution)
• Discussion 4: CNN Architectures & Dropout. (solution)
• Discussion 5: Review of Vision Problems. (solution)
• Discussion 6: Recurrent Neural Networks. (solution)
• Discussion 7: Attention & Transformers. (solution)
• Discussion 8: Pretraining & Imitation. (solution)
• Discussion 9: Policy Gradients & Q-Learning. (solution)
• Discussion 10: Generative Models. (solution)
• Discussion 11: GANs & Adversarial Attacks. (solution)
• Discussion 12: Meta Learning. (solution)

Homeworks

All homeworks are graded for accuracy and it is highly-recommended that you do them. You are given a total of 5 slip days for use only on homeworks. These slip days are intended for emergency use, and as such we employ a strict late policy. There is no additional slack beyond slip days available. See Syllabus for more information.

• Homework 1: Neural Networks & Backprop.
• Homework 2: RNNs & Conv Nets.
• Homework 3: Natural Language Processing.
• Homework 4: Deep Reinforcement Learning.

Lecture Slides

Lecture videos are provided via the course Piazza. See Syllabus for more information.

• Lecture 1: Introduction.
• Lecture 2: ML Basics 1.
• Lecture 3: ML Basics 2.
• Lecture 4: Optimization.
• Lecture 5: Backpropagation.
• Lecture 6: Convolutional Nets.
• Lecture 7: Getting Neural Nets to Train.
• Lecture 8: Computer Vision.
• Lecture 9: Generating Images from CNNs.
• Lecture 10: Recurrent Neural Networks.
• Lecture 11: Sequence To Sequence Models.
• Lecture 12: Transformers.
• Lecture 13: Applications: NLP.
• Lecture 14: Learning-Based Control & Imitation.
• Lecture 15: Reinforcement Learning.
• Lecture 16: Q-Learning.
• Lecture 17: Autoencoders & Latent Variable Models.
• Lecture 18: Variational Autoencoders & Invertible Models.
• Lecture 19: Generative Adversarial Networks.
• Lecture 20: Adversarial Examples.
• Lecture 21: Meta Learning.
• Lecture 22: Guest Lecture.
• Lecture 23: Guest Lecture.
• Lecture 24: Guest Lecture.
• Lecture 25: Guest Lecture.