Stanford CS224N NLP with Deep Learning | Winter 2021 | Lecture 6 - Simple and LSTM RNNs

Показать описание

This lecture covers:
1. RNN Language Models (25min)
2. Other uses of RNNs (8 min)
3. Exploding and vanishing gradients (15 min)
4. LSTMs (20 min)
5. Bidirectional and multi-layer RNNs (12 min)

Professor Christopher Manning
Thomas M. Siebel Professor in Machine Learning, Professor of Linguistics and of Computer Science
Director, Stanford Artificial Intelligence Laboratory (SAIL)

#naturallanguageprocessing #deeplearning

Рекомендации по теме

Комментарии

I can't thank Stanford enough for making the videos public. The quality of these lectures are just out of the world!

sheikhshafayat

This is the greatest illustration of LSTM I have ever watched.

ziangxu

I have returned to this lecture after studying a little bit more. Now I get how well the professor covers all the materials.

nanunsaram

I don’t have enough words to thank you for this course.

avivjan

this is realy amazing! I thank you very much for the positve sharing of your Skills.

mikegher

Regarding vanishing gradients: h are not parameters - W are. Right? And for W, those gradients sum up, i.e., no vanishing. It seems unclear why dJ/dh should be important. Aren't we only interesting in updating W?

Epistemophilos

46:03 Exploding Gradient
1:16:34 Bidirectional and Multi-layer RNNs

jens

1:16:40 Bidirectional and multi-layer RNNs

nanunsaram

This is great, this course is good for understanding basics of nlp and best methods, but why I never heard of comparing actual output with predicted output while talking about reducing the error did i miss something?

meherprudhvi

at 41:00 why is del J / del h even needed?

xyzabs

Stanford CS224N NLP with Deep Learning | Winter 2021 | Lecture 6 - Simple and LSTM RNNs

Stanford CS224N: NLP with Deep Learning | Winter 2021 | Lecture 1 - Intro & Word Vectors

Stanford CS224N NLP with Deep Learning | 2023 | Lecture 8 - Self-Attention and Transformers

Stanford CS224N NLP with Deep Learning | 2023 | Python Tutorial, Manasi Sharma

Stanford CS224N NLP with Deep Learning | 2023 | Lecture 9 - Pretraining

Stanford CS224N NLP with Deep Learning | 2023 | PyTorch Tutorial, Drew Kaul

Stanford CS224N NLP with Deep Learning | 2023 | Hugging Face Tutorial, Eric Frankel

Stanford CS224N: NLP with Deep Learning | Winter 2020 | BERT and Other Pre-trained Language Models

Stanford CS224N: NLP with Deep Learning | Winter 2019 | Lecture 1 – Introduction and Word Vectors

Stanford CS224N NLP with Deep Learning | Winter 2021 | Lecture 6 - Simple and LSTM RNNs

Stanford CS224N NLP with Deep Learning | Winter 2021 | Lecture 2 - Neural Classifiers

Stanford CS224N NLP with Deep Learning | Winter 2021 | Lecture 7 - Translation, Seq2Seq, Attention

Stanford CS224N NLP with Deep Learning | Spring 2022 | Guest Lecture: Scaling Language Models

Stanford CS224N NLP with Deep Learning | Winter 2021 | Lecture 14 - T5 and Large Language Models

Stanford CS224N NLP with Deep Learning | Winter 2021 | Lecture 9 - Self- Attention and Transformers

Stanford CS224N NLP with Deep Learning | Winter 2021 | Lecture 15 - Add Knowledge to Language Models

Stanford CS224N NLP with Deep Learning |Spring 2022|Guest Lecture: Building Knowledge Representation

Stanford CS224N I NLP with Deep Learning | Spring 2022 | Socially Intelligent NLP Systems

Stanford CS224N - NLP w/ DL | Winter 2021 | Lecture 5 - Recurrent Neural networks (RNNs)

Stanford CS224N: NLP with Deep Learning | Winter 2020 | Low Resource Machine Translation

Stanford CS224N: NLP with Deep Learning | Winter 2019 | Lecture 15 – Natural Language Generation

Stanford CS224N NLP with Deep Learning | Winter 2021 | Lecture 18 - Future of NLP + Deep Learning

Stanford CS224N: NLP with Deep Learning | Winter 2019 | Lecture 11 – Convolutional Networks for NLP...

Stanford CS224N NLP with Deep Learning | Winter 2021 | Lecture 13 - Coreference Resolution

Stanford CS224N: NLP with Deep Learning | Winter 2019 | Lecture 6 – Language Models and RNNs