Personal Projects
A handpicked showcase of my favorite projects in machine learning, AI, and software development.
Nizzly - Custom Design E-commerce Platform
Full-stack e-commerce platform enabling users to create and purchase products with custom AI powered designs.
Key Learnings
• Balancing technical complexity with business needs
• Importance of user feedback in early development stages
• Understanding of full end to end data flow from front end all the way to analysis and decision making
TikTok Virality Predictor
Deep learning model using ResNet(2+1)D architecture to predict TikTok video virality.
Key Learnings
• Complex deep learning model architecture selection
• Video data processing and importance of feature engineering
• The importance of a quality data collection process and the power of good data
• How difficult it is to predict virality
Professor Digital Clone
AI digital clone of my professor that can generate educational lectures in the style of my professor using LLM fine-tuning and voice cloning technology.
Key Learnings
• LLM fine-tuning techniques
• How to be resourceful with limited data
• Importance of data preprocessing
• Voice cloning technology
• Structured data preparation for LLMs
Corgi Game Reinforcement Learning
Developed a reinforcement learning agent using PPO algorithm to play "Run, Corgi, Run!".
Key Learnings
• Practical implementation of reinforcement learning algorithms
• Different RL algorithms and their capabilities
• Value of iterating on reward function design and state space design
• Unity ML-Agents framework capabilities
NVIDIA Raccoon Sentry Bot
Autonomous pest control robot using NVIDIA Jetson Nano and computer vision to detect and spray raccoons with water to defend my house.
Key Learnings
• Real-time object detection on edge device
• Combining computer vision with robotics
• Importance of robust testing in real-world conditions
Retinal Abnormality Detector
Computer vision model for detecting diseases in medical retinal scan images.
Key Learnings
• Understanding of AUC metrics and tradeoffs between precision and recall
• Deep learning model architecture design for computer vision
• Importance of balanced datasets in medical AI
• The intense computational power required to train deep learning models