Hi! My name is
Welcome to my website! My name is David Afonso Shepherd and I'm a final-year MEng Computer Science student at the University of Southampton.
I've previously interned with JPMorgan Chase & Co and Spotify, and served as President of the Artificial Intelligence society at the University of Southampton. I was also part of FLARE-X - a joint venture between the University of Southampton, the University of Texas at Austin and the University of Edinburgh - competing in the $11 million XPRIZE Wildfire Competition.
Currently, I'm working with a team of engineers to develop SmartCart v3 - an augmented meal cart designed to help prevent malnutrition in hospital patients by monitoring their food intake - for the University Hospital Southampton NHS FT.
Led development of smart meal cart system for University Hospital Southampton. Implemented computer vision for food intake monitoring and analysis. Designed user-friendly interface for healthcare staff and patients. Integrated with hospital systems for patient data synchronization.
Led development of smart meal cart system for University Hospital Southampton. Implemented computer vision for food intake monitoring and analysis. Designed user-friendly interface for healthcare staff and patients. Integrated with hospital systems for patient data synchronization.
Developed multi-agent reinforcement learning system using PettingZoo framework. Implemented coordinated drone deployment strategies for wildfire suppression. Achieved 40% improvement in fire containment efficiency. Created custom simulation environment with realistic fire spread dynamics.
A collection of deep learning models trained to classify music genres using Mel Spectrograms. The best-performing model (a CNN with batch normalization) achieved an accuracy of 73% on the 10-class genre classification task. This project explored the impact of regularization techniques on model performance.
A K-Means clustering model applied to the text8 dataset to group words based on their semantic relationships using a co-occurrence matrix. This project explored unsupervised learning, word representations and semantic structure discovery in text data.
An XGBoost model trained to predict whether a patient has heart disease based on lifestyle and health indicators. Built as part of a hands-on workshop I delivered on building your first tree-based model, introducing participants to decision trees, ensemble learning and class imbalance.
A recurrent neural network trained to predict Tesla's stock price based on its value over the past 12 days. Built as part of a hands-on workshop I delivered on building your first RNN, introducing participants to sequence modelling, temporal dependencies and time series forecasting.
A convolutional neural network trained to classify images of characters from 'The Simpsons'. Built as part of a hands-on workshop I delivered on building your first CNN, introducing participants to image classification, feature extraction and convolutional layers.
A neural network trained to predict passenger survival on the Titanic using features such as passenger class, sex and family aboard. Built as part of a hands-on workshop I delivered on building your first neural network, demonstrating the fundamentals of data preprocessing, model training and model evaluation.
An analytics dashboard designed to evaluate and visualise the performance of advertising campaigns.
A creative twist on Tetris featuring zero gravity and a multiplayer mode for a fresh strategic experience.
A simulator that recreates the sound of an orchestra performing a given composition, blending musical modelling and procedural audio generation.
A decision-driven third-person adventure game where a player embarks on a medieval-themed quest, shaping their fate through choices and consequences.
A third-person zombie shooter where a player battles waves of relentless zombies. Features multiple rooms, each introducing new challenges and enemy spawns.
A fast-paced racing game where a player strives to beat their own lap record. Features both a single-player mode and a mode with AI-controlled opponents.
Congratulations! You've made it to the end :)
