Introduction to the Course
Text Processing Basics, Tokenization
N-gram Language Models: Part 1
N-gram Language Models: Part 2
NLP Tasks and Paradigms
Supervised Learning
Shallow Neural Networks
Deep Neural Networks
Backpropagation
Gradient Descent and Initialization
Word Representations
Learning Word Representation - Part 1
Learning Word Representation - II
Word Vectors: Other Extensions
Cross-Lingual Representations
RNN Language Model
RNN Applications
RNN for Sequence to Sequence
Decoding Strategies
GRU LSTM
Transfromers Intro
Transformers Part-2
Transformers Part-3
Transformers Part-4
Efficient Transformers
Pretraining
Pretraining Transformer Encoder
Pretraining Transformer Encoder-Decoder
Pretraining Transformer Decoder
More on Pretraining
Applications: Question-Answer
Applications: Question-Answering II
Applications: Dialogue System
Applications:Dialogue System II
Applications: Text-Summarization
Instruction Fine-tuning-I
Instruction Fine-tuning-II
RLHF-I
RLHF-II
Aligning to user preferences via DPO
Prompting-I
Prompting- in-context learning
Advanced Prompting Techniques
Tool-aided Language Models
Automatic Prompt Engineering
PEFT-I
PEFT-II
Efficient fine-tuning for quantized LMs - I
Efficient fine-tuning for quantized LMs - II
Other PEFT Methods
Scaling Laws of LLMs
Modern LLMs and Architectures-I
Modern LLMs Architecture Variations: Positional embeddings
Long Sequence Modelling
RAG
Model Interpretability
Model Interpretability - Multilingual
Model Interpretability - III
Trustworthy LLMs: Taxonomy
Trustworthy LLMs: Machine Unlearning