数据挖掘：理论与算法（2019秋第四章）

第一节

1. The power of parallelism
   The information processing abilities of biological neural systems follow from highly parallel processes operating on representations that are distributed over many neurons.
   The motivation of ANN is to capture this kind of highly parallel computation based on distributed representations.
   Group A
   Using ANN to study and model biological learning processes.
   Group B
   Obtaining highly effective machine learning algorithms, regardless of how closely these algorithms mimic biological processes.
2. 1011: The number of neurons in the human brain
   104: The average number of connections of each neuron
   10-3: The fastest switching time of neurons
   10-10: The switching speed of computers
   10-1: The time required to visually recognize your mother

第二节

3. 
4. Stochastic learnig：知错就改。 Batch learning：批量改

第三节

5. 线性不可分问题拆分成多个线性可分问题的集合应用

第四节

6. 
7. 
8. 
9. 利用momentum去防止over-fitting

第五节

10. 具有记忆功能的网络：

1. Instances are represented by attribute-value pairs.
   Input values can be any real values.
   The target output may be discrete-valued, real-valued, or a vector of several real- or discrete-valued attributes.
   The training samples may contain errors.
   Long training times are acceptable.
   Can range from a few seconds to several hours.
   Fast evaluation of the learned target function may be required.
   The ability to understand the learned function is not important.
   Weights are difficult for humans to interpret.
2. Text Book
   R. O. Duda et al., Pattern Classification, Chapter 6, John Wiley & Sons Inc.
   Tom Mitchell, Machine Learning, Chapter 4, McGraw-Hill.
   http://page.mi.fu-berlin.de/rojas/neural/index.html.html
   Online Demo
   http://neuron.eng.wayne.edu/software.html
   http://facstaff.cbu.edu/~pong/ai/hopfield/hopfieldapplet.html
   Online Tutorial
   http://www.autonlab.org/tutorials/neural13.pdf
   http://www.cs.cmu.edu/afs/cs.cmu.edu/user/mitchell/ftp/faces.html
   课程资料来自清华大学袁博老师学堂在线，非常有用的一门课，欢迎大家一起学习：

数据挖掘：理论与算法课程地址