Given a few labelled samples, semi-supervised learning generally performs much better than supervised learning, semi-supervised learning algorithms are more robust to noise. Label Prediction via Deformed Graph Laplacian for Semi-supervised Learning is presented. A novel curriculum learning approach, dubbed multi-modal curriculum learning, to optimize the quality of semi-supervised image classification is proposed.
NeuCube, a spiking neural network architecture, is presented for FMRI data analysis of Brain cognition, and for obstacle avoidance in prosthetic vision.
Several deep-learning network frameworks are presented for medical image analysis, such as: Computer Aided Detection for Diabetic Retinopathy in Color Fundus Images; Pulmonary nodule detection; Chromosome recognition; Small Lesion Classication in Dynamic Contrast Enhancement MRI for Breast Cancer Early Detection.