| title | Sequence Models & Classic NLP | |
|---|---|---|
| aliases |
|
|
| cssclasses |
|
Word embeddings, RNN/LSTM/GRU, seq2seq with attention, neural machine translation, and classic NLP tasks. The bridge to transformers.
76 documents.
- MIT 6.S191 (2018): Sequence Modeling with Neural Networks · 🎓 lecture · intro
- MIT 6.S191 (2019): Recurrent Neural Networks · 🎓 lecture · intro
- Distributed Representations of Words and Phrases and their Compositionality · 📄 paper · advanced
- Efficient Estimation of Word Representations in Vector Space · 📄 paper · advanced
- Neural Machine Translation by Jointly Learning to Align and Translate · 📄 paper · advanced
- Sequence to Sequence Learning with Neural Networks · 📄 paper · advanced
TABLE WITHOUT ID
link(file.link, default(title, file.name)) AS Document,
default(source, "") AS Type,
default(published, "") AS Date
FROM #topic/sequence-models-rnn and -"atlas"
SORT level ASC, published ASC
(The list above renders in Obsidian with the Dataview plugin. On GitHub, browse Start here or the full index.)
Neural Network Foundations · Transformers & Attention · Language Models & Pretraining