filmov
tv
11-785 Spring 2023 - Recitation 11 - Transformers
Показать описание
Resources:
Errata:
00:38 At the beginning, I ask students to refer to lectures 16-17, when it should be 18-19. Please refer to lectures 18 and 19 by Bhiksha and Abu.
01:16:33 - It should be a lower triangular matrix of ones (not left? My brain is muddled, sorry lol). It is not an upper triangular matrix because we use a comparison of mask == 0 in the attention block. It would be upper triangular if that was inverted.
Errata:
00:38 At the beginning, I ask students to refer to lectures 16-17, when it should be 18-19. Please refer to lectures 18 and 19 by Bhiksha and Abu.
01:16:33 - It should be a lower triangular matrix of ones (not left? My brain is muddled, sorry lol). It is not an upper triangular matrix because we use a comparison of mask == 0 in the attention block. It would be upper triangular if that was inverted.
11-785 Spring 2023 Recitation 1: Your First MLP
11-785 Spring 2023 Recitation 0J: Data Preprocessing
11-785 Spring 2023 - Recitation 14 - Deep Reinforcement Learning (Part 1/2)
11-785 Spring 2023 Recitation 0L: Workflow of a Deep Learning HW
11-785 Spring 2023 Recitation 0C: Introduction to PyTorch
11-785 Spring 2023 Recitation 10: Attention, MT, LAS
11-785 Spring 2023 - Recitation 11 - Transformers
11-785 Spring 2023 Recitation 0F: AWS Fundamentals (Part 1/4)
11-785 Spring 2023 Recitation 0I: What to do if you're struggling
11-785 Spring 2023 Recitation 0E: Introduction to Google Colab
11-785 Spring 2023 - Recitation 12 - GNNs
11-785 Spring 2023 Recitation 0H: Basics of GIT
11-785 Spring 2023 Recitation 0D: Dataset & DataLoaders
11-785 Spring 2023 Recitation 5: CNN Basics & Backprop
11-785 Spring 2023 Recitation 0A: Python & OOP Fundamentals (Part 1/2)
11-785 Spring 2023 Recitation 0G: Debugging and Visualisation (Part 3/3)
11-785 Spring 2023 Recitation 0F: AWS Fundamentals (Part 2/4)
11-785 Spring 2023 Recitation 0G: Debugging and Visualisation (Part 1/3)
11-785 Spring 2023 Recitation 0F: AWS Fundamentals (Part 3/4)
11-785 Spring 2023 - Recitation 14 - Deep Reinforcement Learning (Part 2/2)
11-785 Spring 2023 Recitation 7: CNNs: Verification, Code
11-785 Spring 2023 Recitation 3: Autodiff and backprop
11-785 Spring 2023 Recitation 0G: Debugging and Visualisation (Part 2/3)
11-785 Spring 2023 Recitation 2: Network Optimization, Hyperparameter Tuning
Комментарии