|
課程名稱 |
腦理論
Brain Theory |
|
開課學期 |
107-2 |
|
授課對象 |
學程 神經生物與認知科學學程 |
|
授課教師 |
劉長遠 |
|
課號 |
CSIE7434 |
|
課程識別碼 |
922 U0100 |
|
班次 |
|
|
學分 |
3.0 |
|
全/半年 |
半年 |
|
必/選修 |
選修 |
|
上課時間 |
星期三7,8,9(14:20~17:20) |
|
上課地點 |
資310 |
|
備註 |
曾修類神經網路。
限學士班四年級以上 或 限碩士班以上
總人數上限：32人 |
|
|
|
|
課程簡介影片 |
|
|
核心能力關聯 |
核心能力與課程規劃關聯圖 |
|
課程大綱
|
|
為確保您我的權利,請尊重智慧財產權及不得非法影印
|
|
課程概述 |
The syllabus spans the history of brain theory since its inception. Brain theory is the endeavor to understand mind (thinking, intellect) in terms of its design (how it is built, how it works). Subjects include: neurobiological modeling (Hebbian synapse and Hebbian learning; NMDA/LTE), perception, multilayer perceptron, neural networks, reinforcement leraning, self-organizing map and Hopfield model.
課程內容與類神經網路相同 只有作業與 project 不一樣 延伸的閱讀不一樣 |
|
課程目標 |
principle and applications of neural networks
robot brain and many others...
|
|
課程要求 |
project, home assignments, exam
|
|
預期每週課後學習時數 |
|
|
Office Hours |
另約時間 備註： 預約 |
|
指定閱讀 |
see website
https://www.csie.ntu.edu.tw/~cyliou/red/NN/Classinfo/classinfo.html
and related materials in
https://www.csie.ntu.edu.tw/~cyliou/red/.
|
|
參考書目 |
lecture notes in
https://www.csie.ntu.edu.tw/~cyliou/red/NN/Classinfo/classinfo.html |
|
評量方式
(僅供參考) |
|
|
週次 |
日期 |
單元主題 |
|
第1週 |
2/20 |
Chapter 1 + Chapter 2
perceptron
https://www.csie.ntu.edu.tw/~cyliou/red/NN/Classinfo/classinfo.htm |
|
第2週 |
2/27 |
Chapter 4 + tiling algorithm
perceptron + MLP + BP + tiling
https://www.csie.ntu.edu.tw/~cyliou/red/NN/Classinfo/classinfo.htm
|
|
第3週 |
3/06 |
Lecture #3 Hopfield model
Chapter 6 + three papers J.15+J.20+B.2
J.15 Cheng-Yuan Liou, Shao-Kuo Yuan (1999), Error Tolerant Associative Memory, Biological Cybernetics, vol. 81, pages 331-342.
J.20 Cheng-Yuan Liou and Shiao-Lin Lin (2006), Finite memory loading in hairy neurons, Natural Computing, vol. 5, no. 1, pages 15-42
B.2 Cheng-Yuan Liou (2006), Backbone structure of hairy memory, ICANN, The 16th International Conference on Artificial Neural Networks, September 10-14, Athens Greece, in edited book published by LNCS 4131, Part I, pages 688-697
tutorial 在 B.2 https://www.csie.ntu.edu.tw/~cyliou/red/Publications.htm |
|
第4週 |
3/13 |
Lecture #4 Reinforcement learning
Q-learning
https://www.csie.ntu.edu.tw/~cyliou/red/NN/Demo/demo.html
paper
http://www.derongliu.org/adp/adp-cdrom/Barto1983.pdf
video
https://www.youtube.com/watch?v=xWe58WGWmlk&t=7s |
|
第5週 |
3/20 |
Lecture #5 Self-organizing map
algorithm see
http://www.cis.hut.fi/research/som-research/som.shtml
paper see
The 'Neural' Phonetic Typewriter
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=28&userType=inst
economic states see
https://www.csie.ntu.edu.tw/~cyliou/red/demo/economic/index_eng.html |
|
第6週 |
3/27 |
Lecture #6 Deep learning : Boltzmann machine
By Hinton: https://www.youtube.com/watch?v=vShMxxqtDDs
交作業 一 "tiling algorithm" one A4 page
Hinton's deep learning
http://www.youtube.com/watch?v=vShMxxqtDDs
http://www.youtube.com/watch?v=AyzOUbkUf3M&feature=channel
video by Hugo
http://www.youtube.com/watch?v=AyzOUbkUf3M&feature=channel
https://www.youtube.com/watch?v=p4Vh_zMw-HQ&t=163s
https://www.youtube.com/watch?v=n26NdEtma8U&t=345s
some slides ｏｎ Ｂｏｌｔｚｍａｎｎ ｍａｃｈｉｎｅ
axon.cs.byu.edu/~martinez/classes/678/Slides/Boltzmann.pptx |
|
第7週 |
4/03 |
no class |
|
第8週 |
4/10 |
no class |
|
第9週 |
4/17 |
Lecture #7
NetTalk + BP |
|
第10週 |
4/24 |
Lecture #8
語言
Elamn network
J.35. Cheng-Yuan Liou, Chen-Wei Cheng, Jiun-Wei Liou, and Daw-Ran Liou, Autoencoder for Words, Neurocomputing, vol. 139, pages 84-96, 2014. |
|
第11週 |
5/01 |
Lecture #9 Chapter 4 + Boltzmann machine
Chapter 4 + code in
https://www.csie.ntu.edu.tw/~cyliou/red/NN/Classinfo/classinfo.html
交作業 二 "reinforcement learning" |
|
第12週 |
5/08 |
Lecture #10
Chapter 5 SIR-kernel
read article on hardware
Stochastic Learning with Back Propagation
https://ieeexplore.ieee.org/abstract/document/8702253 |
|
第13週 |
5/15 |
Lecture #11
Chapter 5 SIR-SOM |
|
第14週 |
5/22 |
Lecture #12
SOM applications STD
J.10. Cheng-Yuan Liou and Hsin-Chang Yang (1996). Handprinted character recognition based on spatial topology distance measurement. IEEE Trans. on Pattern Analysis and Machine Intelligence, vol.18, no.9, pages 941-945. SCI&EI, tutorial package, usage
https://www.csie.ntu.edu.tw/~cyliou/red/demo/pr/index_eng.html
自動交易
C.17. Cheng-Yuan Liou, Chung-Hao Tan, Hwann-Tzong Chen, and Jiun-Hung Chen (1998), Agents that Have Desires and Behave Adaptively, The Fifth International Conference on Neural Information Processing, ICONIP, vol. 2, pp. 845-849, Oct. 21-23, Kitakyushu, Japan, preview, Learning Automata Program
交 project "hairy network" |
|
第15週 |
5/29 |
Lecture #13
Chapter 6 applications music
videos |
|
第16週 |
6/05 |
Lecture #14
每位同學 五分鐘報告 project 進度 .ppt
語言複雜度 "complexity of composition"
5 papers slides in B.28
J.26. Cheng-Yuan Liou, Tai-Hei Wu, Chia-Ying Lee (2010), Modelling Complexity in Musical Rhythm, Complexity, vol. 15, no. 4, pages 19-30, 2010.
J.33. Cheng-Yuan Liou, Shen-Han Tseng, Wei-Chen Cheng, and Huai-Ying Tsai (2013), Structural Complexity of DNA Sequence, Computational and Mathematical Methods in Medicine, Special Issue: Biomedical Signal Processing and Modeling Complexity of Living Systems, vol. 2013, Article ID 628036, 11 pages, 2013.
J.37. Cheng-Yuan Liou, Aleksandr A. Simak, and Jiun-Wei Liou, Structure sensitive complexity for symbol-free sequences, Applied Informatics, vol. 2:6, doi: 10.1186/s40535-015-0011-9. 2015.
J.38. Cheng-Yuan Liou, Aleksandr A. Simak, and Wei-Chen Cheng, Complexity analysis of music, Volume 21, Issue S1, Complexity, September/October 2016, Pages 263–268, doi: 10.1002/cplx.21740. 2016.
B.28. Cheng-Yuan Liou, Daw-Ran Liou, Alex A. Simak, and Bo-Shiang Huang (2013), Syntactic sensitive complexity for symbol-free sequence, IScIDE 2013, July 31~August 2, LNCS 8261, pp. 15-23, Bejing, China. slides
+ videos |
|
第17週 |
6/12 |
測驗 2:20pm~3:10pm
3:20pm 解答 |
|