MLP from Scratch: Fashion-MNIST
2024-01-11
Based on the Colab Notebook, explore MLP building from scratch with Python, covering data preprocessing, neural network layers, backpropagation, and hyperparameter tuning.
Iām Justin, a bioengineering student at McGill University in Montreal šØš¦. My research interests include AI+healthcare, cognitively inspired AI, and the intersection of computer vision and natural language processing.
I've worked on many projects from deep learning segmentation of micro-cracks in enamel to prediction of lung metastasis for soft-tissue sarcoma. Beyond being a student, my work as a developer in telehealth increases accessibility to affordable care.
Check out what I'm up to and feel free to reach out!
2024-01-11
Based on the Colab Notebook, explore MLP building from scratch with Python, covering data preprocessing, neural network layers, backpropagation, and hyperparameter tuning.
2024-01-10
This project focuses on predicting alpha-helix secondary structures in amino acids using a RNN with LSTM units. The challenge lies in handling FASTA format sequences, with constraints on model size and dependencies. Utilizing deep learning and NLP techniques, the model, trained in Google Colab and inference implemented in NumPy, demonstrates promising accuracy in protein structure prediction.
2023-12-01
A chronicle of my capstone project. Sharing insights into medical image processing, the challenges of learning with limited data, and the process of evaluating these methods alongside radiomics approaches.