1. Introduction
The codes and slides are used on the Machine Learning course for the first year graduate student in Machine Perception and Interaction Group (MPIG) .
2. References
They are partly based on the course with the same name presented by Andrew Ng at Stanford University and the original can be found at https://www.coursera.org/course/ml. All materials without annotations or marks are copyrighted by their copyright owner.
- All the slides are made with MS Powerpoint 2013
- All the codes are tested in Matlab 2013b (or above) and Octave 3.2.4 (or above). Lower version might cause incompatibilities.
3. Contents
3.1 SUPERVISED LEARNING
- 2_Linear Regression with One Variable
- 3_Linear Regression with Multiple Variables
- 4_Logistic Regression
- 5_Regularization
- 6_Neural Networks Representation
- 7_Neural Networks Learning
- 8_Advice for Applying Machine Learning
- 9_Machine Learning System Design
- 10_Support Vector Machines
3.2 UNSUPERVISED LEARNING
- 11_Clustering
- 12_large Scale Machine learning
- 13_Dimensionality Reduction
- 14_Recommender Systems
- 15_Photo OCR
- 16_Anomaly Detection
3.3 DEEP LEARNING
- 17_Description Application of DeepLearning Framworks
- 18_Introduction to Deeplearning
4. Online Videos
The sections of UNSUPERVISED LEARNING and DEEP LEARNING are delivered by the master students at MPIG. the online videos, presenting the content in detail, are available. Please follow us on WeChat by scanning the following QR code:
