Taking together Stanford cs224n course with support of iPavlov team.
News: https://t.me/dlinnlp
Access code: ipavlov1
Google calendar: https://clck.ru/FBsQs
Community articles links: https://www.mendeley.com/community/dl-in-nlp-course/
- Lecture 2 | Word Vector Representations (word2vec): https://youtu.be/ERibwqs9p38
- Quizz before 07.02.2019 : https://goo.gl/forms/9EZmQhqfhicW0yaO2
- Quizz answers : Evernote Link
- Seminar materials:
- Part 1. Conversational Artificial Intelligence.: https://youtu.be/3nKhzlfaOTE
- Part 2. Course intro: https://youtu.be/U_1xdGUQZ5o
- Part 3. Word vector representations : https://youtu.be/juDdkybtTv0
- Slides Part 2 : https://bit.ly/2Gi9V1z
- Slides Part 3 : https://bit.ly/2WQRtSR
- Additional materials:
- Lecture 1 | Natural Language Processing with Deep Learning: https://youtu.be/OQQ-W_63UgQ
- Lecture 3 | GloVe: Global Vectors for Word Representation: https://youtu.be/ASn7ExxLZws
- Word2Vec Tutorial - The Skip-Gram Model: http://mccormickml.com/2016/04/19/word2vec-tutorial-the-skip-gram-model/
- Efficient Estimation of Word Representations in Vector Space: https://arxiv.org/pdf/1301.3781.pdf
- Distributed Representations of Words and Phrases and their Compositionality: https://arxiv.org/pdf/1310.4546.pdf
- Lecture 4 | Word Window Classification and Neural Networks: https://youtu.be/uc2_iwVqrRI
- Lecture 5 (before 48 minute) | Backpropagation and Project Advice: https://youtu.be/isPiE-DBagM
- Quizz before 14.02.2019 : https://goo.gl/forms/9yDB1KAojvpEABtf2
- Seminar materials:
- Neural networks Part 1 : https://youtu.be/92Ctk9OzlDg
- Additional materials:
- (in Russian) Линейные модели классификации и регрессии: https://habr.com/post/323890/
- Intro in Convolutional Neural Networks for Visual Recognition: http://cs231n.github.io/neural-networks-1
- Lecture 5 (cs231n) | Neural Networks Part 2: https://youtu.be/gYpoJMlgyXA
- (Optional) Lecture 4 (cs231n) | Backpropagation, Neural Networks Part 1: https://youtu.be/i94OvYb6noo
- Quizz before 28.02.2019: https://goo.gl/forms/0dVAtBdUUmeJU7NB2
- Seminar materials:
- Neural networks Part 2 : https://youtu.be/1zv1IJAS9r4
- Slides : https://docs.google.com/presentation/d/1f_-1g0bTp8gvX300HUa2aEUXPXq9LUgnM1zHygM1W10/
- Additional materials:
- (in Russian) Регуляризация нейронных сетей: https://youtu.be/Zz98nDE5b8E
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift : https://arxiv.org/abs/1502.03167
- How Does Batch Normalization Help Optimization? https://arxiv.org/abs/1805.11604
- Machine Learning Glossary: https://clck.ru/FFZ2x
- Lecture 8 | Recurrent Neural Networks and Language Models : https://youtu.be/Keqep_PKrY8
- Lecture 9 (after 40 minute) | Machine Translation and Advanced Recurrent LSTMs and GRUs: https://youtu.be/QuELiw8tbx8?t=2471
- Quizz before 14.03.2019: https://goo.gl/forms/h6Ugof9QENxAAvEG2
- Seminar materials:
- Recurrent Neural Networks and Language Models Part 1 : https://drive.google.com/drive/folders/1-4KBREKificOTissVN7ueNXR8JJYDlqy
- Recurrent Neural Networks and Language Models Part 2 : https://youtu.be/Ms3eOk14Uyc
- Slides : https://docs.google.com/presentation/d/1f_-1g0bTp8gvX300HUa2aEUXPXq9LUgnM1zHygM1W10/
- Additional materials:
- CS 231n Python & NumPy Tutorial : https://clck.ru/FKKEy
- 100 numpy exercises: https://github.com/rougier/numpy-100
- The Unreasonable Effectiveness of Recurrent Neural Networks : http://karpathy.github.io/2015/05/21/rnn-effectiveness/
- The Matrix Calculus You Need For Deep Learning : https://arxiv.org/abs/1802.01528
- Deep contextualized word representations : https://arxiv.org/abs/1802.05365
- Universal Language Model Fine-tuning for Text Classification : https://arxiv.org/abs/1801.06146
- ELMo helps to further improve your sentence embeddings : https://towardsdatascience.com/elmo-helps-to-further-improve-your-word-embeddings-c6ed2c9df95f
- Introducing state of the art text classification with universal language models : http://nlp.fast.ai/
- The Illustrated BERT, ELMo, and co. (How NLP Cracked Transfer Learning) : https://jalammar.github.io/illustrated-bert
- Lecture 13 | Convolutional Neural Networks : https://youtu.be/Lg6MZw_OOLI
- Seminar materials:
- Transfer Learning in NLP : https://youtu.be/aPNf1IRwqN0
- Slides : https://docs.google.com/presentation/d/1rApVsEi-VDyfqIcfoulYTPppR2yXHDV_X_gYPsq4My4/
- Lecture 8 (2019) | Sequence-to-sequence models and Attention : https://youtu.be/7m6noV5-l1E
- The Annotated Encoder-Decoder with Attention : https://clck.ru/FQ8gR