University of Toronto, September – December 2023
- Developed and trained a feedforward backpropagation neural network in MATLAB using real-world cancer diagnosis data (699 patients), achieving 97% classification accuracy distinguishing benign and malignant cases.
- Optimized network architecture and transfer functions (tansig), and interpreted performance using confusion matrices and training plots to ensure robust and reliable predictions.
- Applied statistical methods and cognitive frameworks (Hinton, Kriegel) to analyze model behavior, contributing insights into machine learning decision-making and cognitive representations.
Skills: MATLAB, Neural Networks, Classification, Predictive Modeling
