ECE 6397

Lecture:  11:30am–1:00pm, Tuesday–Thursday (FH215)
Office hours:
1:30pm–2:30pm, Tuesday–Thursday (W308, Engineering Building 2)

TA: Ilker Gurcan, TA’s Email: igurcan@central.uh.edu

References:
[1] The Elements of Statistical Learning, Data Mining, Inference, and Prediction by Trevor Hastie &
[2] Machine learning: A Probabilistic Perspective by Kevin P. Murphy
[3] Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville
[4] Reinforcement learning: An introduction by Richard S. Sutton and Andrew G. Barto

Mathematical background:
[1] Linear Algebra and Its Applications by Gilbert Strang
[2] Matrix Computations by Gene H. Golub and Charles F. Van Loan

Syllabus:

Date Lecture Suggested reading Assignment
22-Aug Linear Model (slides) 7.1–7.3 Murphy  
5-Sept Perceptron (slides) 4.5.1 Hastie  
7-Sept Regularized linear Model  (Ridge, Lasso) (slides) (bias-variance note) 3.4.1–3.4.2 Hastie
12-Sept Introduction to neural networks (Slides) 6.1-6.5 Goodfellow  
14-Sep Stochastic optimization algorithms I (Slides) 8.3 Goodfellow  1 (pdf)
19-Sep Stochastic optimization algorithms II (slides) 8.3 Goodfellow
21-Sep Support vector machine  14.5 Murphy  
26-Sep Support vector machine (slides) 14.5 Murphy 2 (pdf) (answer)
28-Sep Kernel methods 14.7 Murphy  
3-Oct Decision trees, random forests (slides) 9.2.2 & 15 Hastie 5
5-Oct Boosting 10 Hastie  
10-Oct Boosting 10 Hastie 6
12-Oct Midterm    
Principal Component Analysis, Laplacian Eigenmaps  Belkin & Niyogi 2002  
Graph embedding – General framework of dimensionality reduction (Slides) Shuicheng Yan 2007 7
Sparse representation (Slides)  Lecturer’s slides  
Clustering (K-means, Spectral) (slides)  Lecturer’s slides 8
Generative adversarial networks (Slides) Goodfellow et al. 2014 9
Convolutional neural networks LeCun & Bengio 1995  
Convolutional neural networks (Slides) LeCun & Bengio 1995 10
Recurrent networks  10.1 Goodfellow  
Long short term memory network (Slides)  Hochreiter et al. 1997 11
Visualization of Deep Networks (Slides) Lecturer’s slides  
Visualization of Deep Networks Lecturer’s slides 12
Reinforcement learning I (Slides) 4.1-4.4 Sutton 2006  
Reinforcement learning II (Slides) (ppt) 4.1-4.4 Sutton 2006  
Reinforcement learning III (Slides) (ppt) 4.1-4.4 Sutton 2006  
Final project presentation (Description)    

TA Lectures:
Introduction to Python and TensorFlow 1 (slides) (codes)

Online Tensorflow environment (for testing python and tensorflow codes)
https://codeenv.com/env/codeenv/14/tensor-flow/

One thought on “ECE 6397

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s