Table of Contents

Fundamentals

  1. NLP Fundamentals (Part 1) by Vipra

    LLM Architectures Explained: NLP Fundamentals (Part 1)

Word Embedding

NLP Topics

  1. RNN Architecture & Working

    1. A friendly introduction to RNNs : Serrano.Academy
    2. RNNs Clearly Explained!!! : StatQuests

  2. LSTM

    1. Understanding LSTM Networks: Colah's Blog
    2. Analytics Vidhya: Introduction to LSTMs
      ▪ **Limitations of RNNs** ▪ Improvement over RNN: LSTM ▪ Architecture ▪ Forget Gate ▪ Input Gate ▪ Output Gate

  3. MIT Courses

    1. RNN, Transformer & Attentionby MIT 6.S191
    2. MIT 6.S191 (Introduction to Deep Learning) Playlist

  4. NLP Fundamentals

    1. **(Part 1) by Vipra**

      LLM Architectures Explained: Word Embeddings (Part 2)

  5. nGrams

    1. Why Do We Need Them - blog.xrds.acm.org

  6. TF-IDF: **TFIDF by** Ritvikmath

    https://www.youtube.com/watch?v=OymqCnh-APA&list=PLvcbYUQ5t0UH2MS_B6maLNJhK0jNyPJUY&index=66&t=286s

  7. Embeddings

    1. Word Embedding: MachineLearningMastery.com

    2. Word Embedding and Word2Vec: StatQuest

    3. Text Embeddings: cohere.com

      https://docs.cohere.com/docs/the-cohere-platform

  8. Word2Vec

    1. The Illustrated **Word2vec by** Jay Alammar

      https://jalammar.github.io/illustrated-word2vec/

  9. Serrano.Academy Latent Dirichlet Allocation (Part 1 of 2)

Attention

  1. Mechanics of Seq2seq Models With Attention: Jay Alammar
  2. Co-Sine Similarity: cohere.com