For a final year university project, a social media platform was developed enabling users to form communities, start discussions, and comment on them. Tested on CRUD and software engineering principles.

A custom back-end learning project involved creating a straightforward real-time messaging app. Users can chat one-on-one or in group chats, send text messages and images, view active users, etc.

A SaaS platform that leverages AI to enable users to generate various media types and have conversations. Developing this project allowed me to explore Stripe, Clerk authentication, and unique AI APIs.

My first major project using Supabase was a basic music streaming site. Users can upload songs, search and listen to music, as well as like the songs they enjoy.

A note-taking app where users can sign up, log in, and reset passwords easily. It supports rich text formatting, image additions, and publishing notes publicly. Users alse organize notes into nested notebooks.

A platform for dynamic quiz generation. Users can test their knowledge with multiple-choice or fill-in-the-gap questions across various topics. With immediate feedback and score tracking, users enhance their understanding.

In my second year of university, my group and I started an open-source learning platform project, introducing me to full-stack development. This app helps students manage tasks, assignments, exams, and store notes and resources.

A handwritten digit classifier using built using a Convolutional Neural Network (CNN). Used various techniques such as data augmentation, batch normalisation, and dropout to improve the model's performance.

Comparing various classification algorithms to predict whether an adult earns more than $50,000 a year. Emphasis is on feature engineering, data preprocessing with One-Hot Encoding, and model optimization through hyperparameter tuning.

Comparing various regression algorithms to predict house prices in relation to the distance from the coast. Emphasis is on feature engineering, data preprocessing with One-Hot Encoding, and model optimization through hyperparameter tuning.

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.

Implementing algorithms from scratch such as the Nearest Neighbours algorithm. Requires an understanding of the Mathematics behind the algorithms and the ability to implement them.

Be able to use and implement algorithms, with the Lasso and inductive conformal prediction algorithms as examples.

Be able to use and implement algorithms, with the SVM, neural networks, and cross-conformal prediction algorithms as examples.

Implemented various algorithms and techniques learnt during the course, such as Nearest Neighbours, Conformal Prediction, Regression algorithms, data preprocessing, kernels, Neural Networks, SVMs, etc.

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.