lectures
Oxford Deep NLP 2017 course
Lecture slides, video recordings, and coding exercises from Oxford University's 2017 deep learning for natural language processing course, co-taught with DeepMind researchers.
This repository contains the lecture slides and materials from Oxford University's Deep Natural Language Processing (NLP) course, delivered in early 2017 in partnership with researchers from DeepMind. NLP is the field of teaching computers to understand and generate human language — things like translating text, answering questions, or transcribing speech.
The course is advanced and assumes prior knowledge of machine learning. It covers how neural networks (AI systems inspired loosely by the brain) can be applied to language tasks. Topics include word embeddings (turning words into numbers that capture meaning), recurrent neural networks (models that process sequences of words one at a time), and how these can be used for tasks like language translation, speech-to-text, and question answering.
Each lecture has PDF slides and a video recording linked directly in the README. There are also practical coding exercises for hands-on experience with the concepts covered. The course was organized by Phil Blunsom and included lecturers from Carnegie Mellon University, DeepMind, and NVIDIA. The full README is longer than what was provided, but the repository is essentially an open-access archive of the course's educational materials.
Where it fits
- Work through the full Oxford Deep NLP 2017 curriculum to build a foundation in neural networks for language tasks.
- Use the practical coding exercises to get hands-on experience with word embeddings and recurrent neural networks.
- Watch video lectures from DeepMind and CMU researchers on machine translation, speech recognition, and question answering.