This repository provides code and assignments for an Imperial College Mathematics department Deep Learning course. It targets PhD students with no prior experience, offering foundational knowledge, practical tutorials in TensorFlow/PyTorch, and insights into state-of-the-art techniques like GANs and VAEs. The goal is to equip students with in-demand deep learning skills.

How It Works

The course utilizes a practical, hands-on approach, integrating TensorFlow and PyTorch tutorials with theoretical underpinnings. Students are expected to fork the repository, implement solutions to assignments as Python scripts, and potentially engage in oral assessments. This methodology aims to bridge theoretical concepts with practical application, enabling students to build and train their own deep neural networks.

Quick Start & Requirements

• Install: pip install tensorflow pytorch numpy (Anaconda is preferred for PyTorch and TensorFlow).
• Prerequisites: Python 3, TensorFlow, PyTorch, NumPy, Jupyter Notebook. OpenAI Gym is also mentioned for installation.
• Setup: Installation via Anaconda or pip is recommended. Links to installation guides for Anaconda, Jupyter, TensorFlow, PyTorch, torchtext, and OpenAI Gym are provided.

Highlighted Details

• Covers foundational Deep Learning concepts.
• Includes practical tutorials using TensorFlow and PyTorch.
• Explores advanced topics: CNNs, RNNs, Reinforcement Learning, GANs, VAEs.
• Coursework involves implementing solutions in Python scripts.

Maintenance & Community

The repository is associated with Imperial College Mathematics department faculty and PhD students, including Kevin Webster and Pierre Richemond. Kai Arulkumaran, a notable PyTorch contributor, also provided materials.

Licensing & Compatibility

The repository's license is not explicitly stated in the README.

Limitations & Caveats

The README does not specify the license, which may impact commercial use or integration into closed-source projects. It focuses on academic use within the Imperial College Mathematics department.