Recent research on brain-inspired Modeling and its applications

Dr. Jie Yang, prófessor við Institute of Image Processing and Pattern Recognition, School of Electronics and Information, Shanghai Jiaotong University flytur fyrirlesturinn Recent research on brain-inspired Modeling and its applications

Abstract:
Visual saliency is the selective mechanism of human visual attention. We apply the Normalized graph cut (Ncut) to salient region detection, and induce a saliency map by Ncut eigenvectors for better visual clustering. We embed saliency detection in an adaptive multi-level merging scheme to discover cluster information conveyed by Ncut eigenvectors.
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.

Fyrirlesturinn er haldinn á vegum Rafmagns- og tölvuverkfræðideildar og IEEE á Íslandi.