Projects

Real-time Object Detection System

Developed a computer vision system using PyTorch and OpenCV for real-time object detection. Implemented custom data preprocessing pipeline and model optimization techniques. Currently exploring TensorRT acceleration for embedded deployment.

FPGA Neural Network Accelerator

Building a custom neural network accelerator using FPGA development board. Learning hardware description languages (VHDL) and implementing basic matrix multiplication cores. Exploring efficient memory architectures for ML acceleration.

Retail Analytics ML Pipeline

Enhanced Amazon's retail analytics with machine learning. Built demand forecasting models using Python and scikit-learn, processing millions of transactions. Implemented automated feature engineering and model retraining pipelines.