A collection of deep learning experiments and projects, exploring various architectures and applications.
Each branch contains its own dedicated work, including:
- Source code(ipynb) for the specific model or task
- Training results and evaluations
- Visualisations such as graphs and performance GIFs
For example, the reinforcement_learning branch showcases a Deep Q-Network (DQN) implementation on the Pendulum environment, complete with trained weights and animated rollouts.