Deep Learning For Natural Language Processing
Complete crash-course on Deep Learning applied to text. From basic text classification, all the way to Large Language Models, Reinforcement Learning From Human Feedback etc.
Term: Summer Semester
Time: Tuesdays, 13:30-15:20 AM
Course Overview
This course covers both foundation and up-to-date methodologies for Natural Language Processing (NLP), that today build the backbone of popular AI tools. Starting from the basics (mathematics of deep learning, backpropagation etc.), you will learn how more and more advanced models can understand natural language. By the end of this course, you will be gain understanding of:
- Key machine learning paradigms and concepts
- Both basic and advanced machine learning algorithms/models applied to NLP
- Evaluation, optimisation, and comparison model performance
- Applying NLP models and techniques to real-world problems
Prerequisites
- Basic knowledge of linear algebra and calculus
- Programming experience in Python
- Probability and statistics fundamentals
Lectures recordings
Available publicly on YouTube
Schedule
| Week | Date | Topic | Materials |
|---|---|---|---|
| 1 | Apr 22 | NLP tasks and evaluation | |
| 2 | Apr 29 | Mathematical foundations of deep learning | |
| 3 | May 6 | Log-linear models | |
| 4 | May 13 | Deep Neural Networks | |
| 5 | May 20 | Language models and word embeddings | |
| 6 | May 27 | Learning Word Embeddings | |
| 7 | Jun 3 | Recurrent neural networks | |
| 8 | Jun 10 | Autoregressive encoder-decoder with RNNs and attention | |
| 9 | Jun 24 | Transformers, Self-attention and BERT | |
| 10 | Jul 1 | Decoder-only Models and GPT | |
| 11 | Jul 8 | Contemporary LLMs and Explainability | |
| 12 | Jul 15 | Exam simulation | |
| 13 | Jul 22 | Guest lecture (Mechanistic interpretability, Privacy and Security in LLMs, Culture-aware LLMs) |