Differences

This shows you the differences between two versions of the page.

--- start [2012/08/30 18:37] – hj
+++ start [2019/08/22 21:28] (current) – hj
@@ Line 1: / Line 1: @@
 ~~NOTOC~~
-====== CSE 6328E Speech and Language Processing (Winter 2012) ======
+====== EECS 6327 Probabilistic Models & Machine Learning (Winter 2018) ======
 ===== Description  =====
-The course introduces some basic statistical modeling methods in pattern recognition and machine learning and their applications to speech and language processing. The covered topics may include:
+The course introduces some probabilistic models and machine learning methods. The covered topics may include:
-  * Bayesian Decision theory, Generative vs Discriminative modeling
+  * Bayesian Decision theory, Generative vs Discriminative modelling
-  * Generative Models - multivariate Gaussian, Gaussian mixture model (GMM), hidden Markov model (HMM), Multinomial, Markov chain model, n-gram, graphical models
+  * Generative Models (1) - multivariate Gaussian, Gaussian mixture model (GMM),  Multinomial, Markov chain model, n-gram
-  * Discriminative Models - linear discriminant, logistic regression, support vector machines (SVM), neural networks (NN), sparse kernel machines
+  * Generative Models (2) - graphical models, directed vs. indirected graphical models, exact inference, approximate inference (loopy belief propagation, variational inference, Monte Carlo methods)
-  * Statistical Modeling Methods - maximum likelihood estimation (MLE), Expectation-Maximization (EM), discriminative training (DT)
+  * Discriminative Models (1) - linear discriminant, linear regression, lasso, logistic regression, support vector machines (SVM), sparse kernel machines
-  * Some selected applications - speech recognition, text categorization, machine translation, spoken language processing
+  * Discriminative Models (2) - neural networks (NN),  back-propagation,  deep learning,   auto-encoder; recurrent neural networks, convolutional neural networks
+  * Advanced models: hidden Markov model (HMM),  Latent Dirichlet Allocation (LDA), Conditional Random Fields (CRF), Convolutional Neural Nets, Recurrent Neural Nets and LSTMs
+  * Advanced topics: Learnability, Gaussian Processes, Ensemble Methods, Reinforcement Learning, etc.
-The above methods are equally applicable to other research areas, such as data mining, information retrieval, computer vision, computational linguistics and so on.
 ===== Announcements =====
@@ Line 19: / Line 20: @@
 ===== Lecture Times =====
-  * Section M: Tuesdays and Thursdays, 11:30am - 1:00pm, FRQ 045 (Farquharson Life Sciences building)
+  * Section A: Tuesdays and Thursdays, 4:00pm - 5:30pm, located at <del>BC228</del> **SC 214**.
 ===== Lecturer =====
   * Prof. [[http://www.cse.yorku.ca/~hj|Hui Jiang]] @ CSEB3014