COMP / ELEC / STAT 602, fall 2015
Short course description: Advanced topics in ANN theories, with a focus on learning high-dimensional manifolds with neural maps (Self-Organizing Maps and variants, Learning Vector Quantization, both unsupervised and supervised paradigms) (unsupervised learning in general). Application to clustering, classification, dimension reduction, sparse representation. Comparison with "gold standards" through examples from image and signal processing. The course will be a mix of lectures and seminar style discussions with active student participation, based on recent research publications. Students will have access to research software environment to do simulations. Want a small glimpse in layman's terms?
|