Pattern Recognition (Fall 2018)

Slides

Related Materials

Introduction    Data

Tutorial 01

Tutorial 02

1. UCI Machine Learning Repository

2. A tutorial on Principal Components Analysis

3. Feature selection techniques in bioinformatics

Model evaluation and selection

Linear model

Tutorial 03    Lab 1

Assignment 1 due date: Oct. 16

fisherLDAExperiment.m

Decision Tree

Tutorial 04    

Decision tree implemented in matlab code

Source codes directory

Neural network

Assignment 2 due date: Nov. 6

SVM

Lab 2

Naive Bayes

Ensumble Learning

Clustering Analysis

Tutorial 05    

Assignment 3 due date: Jan. 2

Dimension Reduction

Fundamentals for Deep Learning

1. Demo for linear regression

2. Demo for softmax regression

3. An easy tutorial for understanding backpropagation

4. Caffe: The most widely used deep learning framework

5. Windows Caffe, Installation Guide

6. Digit classification demo. Classify an image with a digit using your trained LeNet. (For instructions, refer to Installation Guide)

7. Cifar10 test demo. Classify an image using your trained Cifar10 network. (For instructions, refer to Installation Guide)

8. Self Data Training. This ZIP file contains all the necessary files to conduct self-data training mentioned in Installation Guide.

9. K. He et al., Deep Residual Learning for Image Recognition, CVPR 2016

10. G. Huang et al., Densely Connected Convolutional Networks, CVPR 2017

11. J. Redmon et al., Yolo: 9000 better faster stronger, CVPR 2017

12. Learn to configure YoloV2 and try to solve your own detection task, https://github.com/AlexeyAB/darknet

1. Lin Zhang, Junhao Huang, et al., Vision-based parking-slot detection: A DCNN-based approach and a large-scale benchmark dataset, IEEE Trans. Image Processing, 27 (11) 5350-5364, 2018. Project site: https://cslinzhang.github.io/deepps/ 

2. Z. Cao et al., Realtime multi-person 2D pose estimation using part affinity fields, CVPR 2017

3. CMU OpenPose Libary, https://github.com/CMU-Perceptual-Computing-Lab/openpose 

GANs and Their Applications in Image Generation

1. I.J. Goodfellow et al., Generative adversarial nets, NIPS, 2014

2. A. Radford et al., Unsupervised representation learning with deep convolutional generative adversarial networks, ICLR, 2016

3. M. Arjovsky et al., Towards principled methods for training generative adversarial networks, ICLR, 2017

4. M. Arjovsky et al., Wasserstein GAN, arXiv, 2017

5. I. Gulrajani et al., Improved training of Wasserstein GANs, arXiv, 2017

6. P. Isola, J. Zhu, T. Zhou, and A.A. Efros, Image-to-image translation with conditional adversarial networks, CVPR, 2017

7. J. Zhu et al., Unpaired image-to-image translation using cycle-consistent adversarial networks, arXiv, 2017

8. C. Ledig et al., Photo-realistic single image super-resolution using a generative adversarial network, CVPR, 2017

9. A. Shrivastava et al., Learning from simulated and unsupervised images through adversarial training, CVPR, 2017

*Matlab Tutorial

Examples for Matlab Tutorial

A matlab tutorial document

Program:

Origninality of the selected topic or applied method (published since 2010) (10');

Performance (10')

Complexity of the project (workload) (5')

Report:

1. (5'); 2. (8'); 3.(5'); 4. (7'); 5. (3'); Clarity (2')

《机器学习》

周志华

清华大学出版社

Pattern Classification

Richard O. Duda, Peter E. Hart, David G. Stork

模式识别

张学工

清华大学出版社