ECE544NA is a permanent special-topics course in pattern recognition. Content varies every year, but usually includes error metrics (e.g., information-theoretic and perceptron-based) and optimization (e.g., neural network, Bayesian, stochastic, and convex programming techniques) for the supervised, semi-supervised, and unsupervised estimation of probability densities, feature selection, regression and classification. In fall 2013, ECE 544NA will cover the material usually included in this course, but with a particular emphasis on neural networks. This emphasis on neural networks is prompted by the dramatic success of pre-trained deep belief networks, recently, in many pattern recognition applications.
- Instructor: Mark Hasegawa-Johnson. Office Hours: W2-3pm, 2011 Beckman.
- TA: Sujeeth Bharadwaj. Office Hours: W5-7pm, 168 Everitt.
- Lectures: Tuesdays and Thursdays, 11:00-12:20
- Lecture Location: 204 Transportation Building
- Recommended Text: Either Neural Networks for Pattern Recognition (NNPR) or Pattern Recognition and Machine Learning (PRML), Christopher M. Bishop. The former text is about five pounds lighter; the latter text has a lot more details in each proof, and a lot of interesting new material. I actually own both, but tend to carry the lighter one around with me.
- Syllabus
- Homework
- Notes
- Exam
- Related Courses