Built a neural network from scratch to teach a Pacman agent. Used various techniques such as batch normalisation, dropout, momentum, learning rate decay and more to improve performance.

Practicing various algorithms and techniques. This includes supervised, unsupervised, and reinforcement learning algorithms, as well as feature engineering, data preprocessing, and hyperparameter tuning.

Practicing various Reinforcement Learning algorithms and techniques. This includes Q-Learning, Deep Q-Learning, and Asynchronous Advantage Actor-Critic (A3C) algorithms.

A custom Q-Learning agent learns to play Pacman. Required foundational Mathematics knowledge and understanding of the Q-Learning algorithm.

Exploring valuation of options using methods like Black-Scholes, binomial trees, and Monte Carlo. Also includes theoretical aspects of put-call parity and financial arbitrage opportunities.

Focusing on learning generative models, using third-party models and using advanced techniques. This includes techniques such as transfer learning, LLM Agents, and Generative Models.

Pacman agent plays to win the game while handling stochasticity in the movement of agent and ghosts. Uses Markov Decision Processes, Value Iteration and other enhancements.

Segmenting images using various techniques. Specifically, used models of biological vision systems such as Simple and Complex cells, and Gabor filters.

Solutions to quizzes where various low-level and mid-level vision techniques were covered. These techniques include edge detection, image segmentation, and image filtering.