User contributions for Z238zhan
Jump to navigation
Jump to search
28 March 2025
- 15:3215:32, 28 March 2025 diff hist +1,604 stat940W25-presentation →Group 10 Presentation: Accelerating Large Language Model Decoding with Speculative Sampling
- 15:2515:25, 28 March 2025 diff hist +76 stat940W25-presentation →Group 13 Presentation:
- 15:2415:24, 28 March 2025 diff hist +1,808 stat940W25-presentation →Group 9 Presentation: Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
- 15:1515:15, 28 March 2025 diff hist +431 stat940W25-presentation →Related work
- 15:1315:13, 28 March 2025 diff hist +1,116 stat940W25-presentation →Group 7 Presentation: Attention with Markov: A Framework for Principled Analysis of Transformers via Markov Chains
- 15:0815:08, 28 March 2025 diff hist +21 stat940W25-presentation →Related work
- 15:0715:07, 28 March 2025 diff hist +266 stat940W25-presentation →Related work
- 15:0515:05, 28 March 2025 diff hist +1,013 stat940W25-presentation →Group 5 Presentation: Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models
- 14:3514:35, 28 March 2025 diff hist +1,181 stat940W25-presentation →Group 4 Presentation: Learning spatiotemporal dynamics with a pretrained generative model
- 14:2614:26, 28 March 2025 diff hist +331 stat940W25-presentation →Group 1 Presentation: Universal Physics-Informed Neural Networks: Symbolic Differential Operator Discovery with Sparse Data
9 February 2025
- 22:1022:10, 9 February 2025 diff hist +308 stat940W25 →Question
- 21:5921:59, 9 February 2025 diff hist +138 stat940W25 →Solution
7 February 2025
- 23:2923:29, 7 February 2025 diff hist −2 stat940W25 →Solution
- 23:2823:28, 7 February 2025 diff hist +2,009 stat940W25 No edit summary
- 22:1522:15, 7 February 2025 diff hist +3,043 stat940W25 No edit summary
31 January 2025
- 17:2517:25, 31 January 2025 diff hist +72 stat940W25 →Solution
- 01:4801:48, 31 January 2025 diff hist +2,782 stat940W25 No edit summary
- 01:4601:46, 31 January 2025 diff hist +76 N File:LSTM v.s. Dense model.png The plot of the accuracy of the LSTM model and the dense model current
30 January 2025
- 20:2220:22, 30 January 2025 diff hist +762 stat940W25 No edit summary
- 20:1520:15, 30 January 2025 diff hist +39 N File:Recurrent NN .png Screenshot from Lecture 8 current
28 January 2025
- 18:4418:44, 28 January 2025 diff hist +3,287 stat940W25 No edit summary
- 18:3518:35, 28 January 2025 diff hist +86 N File:different pooling strategies.png Validation accuracy for different pooling strategies on CIFAR-10 dataset current
26 January 2025
- 23:1523:15, 26 January 2025 diff hist +71 stat940W25 →Solution
- 23:0623:06, 26 January 2025 diff hist +308 stat940W25 →Solution
24 January 2025
- 00:4400:44, 24 January 2025 diff hist +7,042 stat940W25 No edit summary
- 00:3200:32, 24 January 2025 diff hist +94 N File:validation loss.jpg Validation loss with different L2 regularization and patience for early stopping current
- 00:2600:26, 24 January 2025 diff hist +5,044 stat940W25 No edit summary
- 00:1700:17, 24 January 2025 diff hist +63 N File:training loss.jpg Plot of training loss for different dropout rates current
21 January 2025
- 18:4618:46, 21 January 2025 diff hist +39 stat940W25 →Solution
- 18:4418:44, 21 January 2025 diff hist +11 stat940W25 →Solution
- 18:4018:40, 21 January 2025 diff hist +6 stat940W25 →Answer
- 18:3418:34, 21 January 2025 diff hist 0 stat940W25 →Solution
- 18:3318:33, 21 January 2025 diff hist +485 stat940W25 →Solution
- 18:1318:13, 21 January 2025 diff hist +16 stat940W25 →Solution
- 18:1018:10, 21 January 2025 diff hist +2 stat940W25 →Question
- 18:0618:06, 21 January 2025 diff hist +98 stat940W25 →Solution
20 January 2025
- 23:3723:37, 20 January 2025 diff hist +2 stat940W25 →Answer
- 23:3623:36, 20 January 2025 diff hist +1,542 stat940W25 No edit summary
19 January 2025
- 23:3023:30, 19 January 2025 diff hist +3,953 stat940W25 No edit summary
18 January 2025
- 23:4623:46, 18 January 2025 diff hist +2,543 stat940W25 No edit summary
15 January 2025
- 19:3419:34, 15 January 2025 diff hist +3,186 stat940W25 Add exercise 1.3
- 19:2819:28, 15 January 2025 diff hist +118 N File:Visualization 3D.jpg Visualize a single linear equation with three inputs associates a value y with each point in a 3D space. current
- 19:1719:17, 15 January 2025 diff hist +118 N File:Screenshot 2025-01-15 at 5.52.47 PM.png Visualize a single linear equation with three inputs associates a value y with each point in a 3D space. current
