Lecture 1 - Introduction to the Course
Lecture 2 - Text Processing Basics, Tokenization
Lecture 3 - N-gram Language Models - Part 1
Lecture 4 - N-gram Language Models - Part 2
Lecture 5 - NLP Tasks and Paradigms
Lecture 6 - Tutorial 1
Lecture 7 - Supervised Learning
Lecture 8 - Shallow Neural Networks
Lecture 9 - Deep Neural Networks
Lecture 10 - Backpropagation
Lecture 11 - Gradient Descent and Initialization
Lecture 12 - Tutorial 2
Lecture 13 - Word Representation
Lecture 14 - Learning Word Representation - Part I
Lecture 15 - Learning Word Representation - Part II
Lecture 16 - Word Vectors: Other Extensions
Lecture 17 - Cross-Lingual Representations
Lecture 18 - Tutorial 3
Lecture 19 - RNN Language Models
Lecture 20 - RNN Applications : Text Generation, Sequence Labeling, Text Classification
Lecture 21 - RNN for Sequence to Sequence
Lecture 22 - Decoding Strategies
Lecture 23 - Better RNN Units : GRU, LSTM
Lecture 24 - Tutorial 4
Lecture 25 - Introduction to Transformers
Lecture 26 - Transformers - Part 2
Lecture 27 - Transformers - Part 3
Lecture 28 - Transformers - Part 4
Lecture 29 - Efficient Transformers
Lecture 30 - Tutorial 5
Lecture 31 - Pretraining
Lecture 32 - Pretraining Transformer Encoder
Lecture 33 - Pretraining Transformer Encoder, Encoder-Decoder
Lecture 34 - Pretraining Transformer Decoder
Lecture 35 - More on Pretraining
Lecture 36 - Tutorial 6
Lecture 37 - Applications : Question Answering - I
Lecture 38 - Applications : Question Answering - II
Lecture 39 - Applications : Dialogue Systems - I
Lecture 40 - Applications : Dialogue Systems - II
Lecture 41 - Applications : Text Summarization
Lecture 42 - Tutorial 7
Lecture 43 - Instruction Fine-Tuning - I
Lecture 44 - Instruction Fine-Tuning - II
Lecture 45 - Reinforcement Learning from Human Feedback - I
Lecture 46 - Reinforcement Learning from Human Feedback - II
Lecture 47 - Aligning to User Preferences via Direct Preference Optimization
Lecture 48 - Tutorial 8
Lecture 49 - Prompting - I
Lecture 50 - Prompting : Why does in-context learning work?
Lecture 51 - Advanced Prompting Techniques
Lecture 52 - Tool-aided Language Models
Lecture 53 - Automatic Prompt Engineering
Lecture 54 - Tutorial 9
Lecture 55 - Parameter-efficient fine-tuning - I
Lecture 56 - Parameter-efficient fine-tuning - II
Lecture 57 - Efficient fine-tuning for quantized LMs - I
Lecture 58 - Efficient fine-tuning for quantized LMs - II
Lecture 59 - Other Parameter Efficient Methods: Pruning, Distillation
Lecture 60 - Tutorial 10
Lecture 61 - Scaling Laws of LLMs
Lecture 62 - Modern LLMs and Architecture Variations - I
Lecture 63 - Modern LLMs and Architecture Variations: Positional Embeddings
Lecture 64 - Long Sequence Modeling
Lecture 65 - Retrieval Augmented Generation
Lecture 66 - Tutorial 11
Lecture 67 - Model Interpretability
Lecture 68 - Model Interpretability - Multilingual
Lecture 69 - Model Interpretability - III
Lecture 70 - Trustworty LLMs : Taxonomy
Lecture 71 - Trustworty LLMs : Machine Unlearning
Lecture 72 - Tutorial 12