Research/NLP_Stanford
-
Multimodal Deep Learning - 5. Evaluation / 6. Where to next?Research/NLP_Stanford 2024. 6. 30. 10:54
※ Writing while taking a course 「Stanford CS224N NLP with Deep Learning」 ※ https://www.youtube.com/watch?v=5vfIT5LOkR0&list=PLoROMvodv4rMFqRtEuo6SGjY4XbRIVRd4&index=22Lecture 16 - Multimodal Deep Learninghttps://web.stanford.edu/class/archive/cs/cs224n/cs224n.1234/slides/Multimodal-Deep-Learning-CS224n-Kiela.pdfI also have to tell you how you're going to check that the multimodal system is actua..
-
Multimodal Deep Learning - 4. Multimodal foundation modelsResearch/NLP_Stanford 2024. 6. 29. 21:58
※ Writing while taking a course 「Stanford CS224N NLP with Deep Learning」 ※ https://www.youtube.com/watch?v=5vfIT5LOkR0&list=PLoROMvodv4rMFqRtEuo6SGjY4XbRIVRd4&index=22Lecture 16 - Multimodal Deep Learninghttps://web.stanford.edu/class/archive/cs/cs224n/cs224n.1234/slides/Multimodal-Deep-Learning-CS224n-Kiela.pdfIf you have a BERT model and you have a bunch of images, how are you going to turn th..
-
Multimodal Deep Learning - 2. Features and fusion / 3. Contrastive modelsResearch/NLP_Stanford 2024. 6. 29. 15:21
※ Writing while taking a course 「Stanford CS224N NLP with Deep Learning」 ※ https://www.youtube.com/watch?v=5vfIT5LOkR0&list=PLoROMvodv4rMFqRtEuo6SGjY4XbRIVRd4&index=22Lecture 16 - Multimodal Deep Learninghttps://web.stanford.edu/class/archive/cs/cs224n/cs224n.1234/slides/Multimodal-Deep-Learning-CS224n-Kiela.pdfIf all of this multimodal stuff is cool and useful and doesn't look that difficult, w..
-
Multimodal Deep Learning - 1. Early modelsResearch/NLP_Stanford 2024. 6. 29. 12:50
※ Writing while taking a course 「Stanford CS224N NLP with Deep Learning」 ※ https://www.youtube.com/watch?v=5vfIT5LOkR0&list=PLoROMvodv4rMFqRtEuo6SGjY4XbRIVRd4&index=22Lecture 16 - Multimodal Deep Learninghttps://web.stanford.edu/class/archive/cs/cs224n/cs224n.1234/slides/Multimodal-Deep-Learning-CS224n-Kiela.pdfWhy do we care about multimodality?There are a couple of good reasons in general for ..
-
Model Analysis & ExplanationResearch/NLP_Stanford 2024. 6. 29. 08:04
※ Writing while taking a course 「Stanford CS224N NLP with Deep Learning」 ※ https://www.youtube.com/watch?v=f_qmSSBWV_E&list=PLoROMvodv4rMFqRtEuo6SGjY4XbRIVRd4&index=17&t=1sLecture 17 - Model Analysis and Explanationhttps://web.stanford.edu/class/archive/cs/cs224n/cs224n.1234/slides/cs224n-2023-lecture18-analysis.pdfIf you get high accuracy on the in-domain test set, you are not guaranteed high a..
-
Reinforcement Learning from Human Feedback (RLHF)Research/NLP_Stanford 2024. 6. 24. 12:31
※ Writing while taking a course 「Stanford CS224N NLP with Deep Learning」 ※ https://www.youtube.com/watch?v=SXpJ9EmG3s4&list=PLoROMvodv4rMFqRtEuo6SGjY4XbRIVRd4&index=10Lecture 10 - Prompting & Reinforcement Learning from Human Feedback (RLHF)https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1234/slides/cs224n-2023-lecture11-prompting-rlhf.pdf So we're going to explicitly try to satisfy huma..
-
PromptingResearch/NLP_Stanford 2024. 6. 24. 07:10
※ Writing while taking a course 「Stanford CS224N NLP with Deep Learning」 ※ https://www.youtube.com/watch?v=SXpJ9EmG3s4&list=PLoROMvodv4rMFqRtEuo6SGjY4XbRIVRd4&index=10Lecture 10 - Prompting & Reinforcement Learning from Human Feedback (RLHF)https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1234/slides/cs224n-2023-lecture11-prompting-rlhf.pdfGPT-3 is 175 billion parameters. So it's another ..
-
PretrainingResearch/NLP_Stanford 2024. 6. 23. 13:16
※ Writing while taking a course 「Stanford CS224N NLP with Deep Learning」 ※ https://www.youtube.com/watch?v=DGfCRXuNA2w&list=PLoROMvodv4rMFqRtEuo6SGjY4XbRIVRd4&index=9Lecture 9 - Pretraininghttps://web.stanford.edu/class/archive/cs/cs224n/cs224n.1234/slides/cs224n-2023-lecture9-pretraining.pdf Why should this pretraining, fine-tuning, two-part paradigm help? Pretraining provides some starting p..