|Instructor: Prof. Richard Zanibbi (web page; rxzvcs at rit dot edu )
Office Hrs: W 1:30-2:30pm, F 12:30-2:30pm
Lectures: MWF 2:30-3:25pm, GOL-3445
RIT Academic Calendar
Week Topics Assign/Proj Presentations   Classification 1 Overview, Nearest Neighbor Classification 2 Bayesian Decision Theory and Linear Classifiers 3 Dimensionality Reduction (PCA, LDA) A1 due 4 Support Vector Machines Class. Pres. #1 *W/T: Career Fair 5 Ensembles: AdaBoost, Random Forests A2 due; Proj. 1 assigned 6 Ensembles: CNN and 'Deep' Neural Nets Class. Pres. #2 Segmentation 7 Segmentation + Clustering (incl. k-means) Proj. 1 due 8 Segmentation, continued Seg. Pres. #1 9 [ -- Spring Break -- ] 10 Object Detection: Joint Class. + Seg. Proj. 2 assigned 11 Segmentation, continued A3 due Seg. Pres. #2 Parsing 12 Parsing Overview, Structural Pattern Rec. Parsing Pres. #1 13 Sequences: HMM, LSTM/BLSTM Proj. 2 due & P3 assigned 14 Hierarchies: Stochastic Context-Free Grammars A4 due Parsing Pres. #2 15 Parsing, Cont'd. Proj. 3 due;Project Presentations 16 Class Monday; -- Exam Week -- A5 due
Readings: this course makes use of a variety of texts, including Pattern Classification (Duda, Hart and Stork), Elements of Statistical Learning (Hastie, Tibshirani and Friedman), Pattern Recognition and Machine Learning (Bishop), Boosting (Freund and Schapire), C4.5 (Quinlan), along with research papers and other sources. Readings will be provided through MyCourses.