New framework renders AI more trustworthy for cancer subtyping

Medical artificial intelligence (AI) faces a fundamental challenge: uncertainty quantification. Artificial neural networks ...
IEEE

RandomViG: Random Vision Graph Neural Network for Image Classification

Abstract: Vision Graph Neural Network (ViG) is the first graph neural network model capable of directly processing image data. The community primarily focuses on the model structures to improve ViG’s ...
GitHub

Neural Network from Scratch with NumPy

This project was a self-directed challenge to understand the mathematical and computational foundations of neural networks. Using a framework like PyTorch makes it easy to build networks without truly ...
IEEE

Development and Comparative Analysis of Deep Learning Models for Multiclass Classification of Liver Conditions in Ultrasound Imaging

Abstract: Early and accurate classification of liver conditions is critical for effective treatment and improved patient outcomes. While biopsy is invasive and visual interpretation of ultrasound ...