COMP / ELEC / STAT 602, fall 2017
Short course description: Advanced topics in Artificial Neural Network theories, with a focus on learning high-dimensional complex manifolds with neural maps (Self-Organizing Maps and variants, Learning Vector Quantization variants, both unsupervised and supervised paradigms). Application to data mining, clustering, classification, dimension reduction, sparse representation. Comparison with "gold standards" on data of various complexities. Examples through image and signal processing, bioinformatics, brain mapping from fMRI, environmental mapping from spectral imagery. The course will be a mix of lectures and seminar style discussions with active student participation, based on recent research publications. Strong coding skills in MATLAB, R, or C are assumed. Students may also have access to research software environment to do simulation experiments.
Want a small glimpse in layman's terms?