|
課程名稱 |
腦理論
Brain Theory |
|
開課學期 |
106-2 |
|
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 |
|
Ceiba 課程網頁 |
http://ceiba.ntu.edu.tw/1062CSIE7434_ |
|
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 various associative memories. |
|
課程目標 |
Brain theory is the endeavor to understand mind (thinking, intellect, 語言 視覺等) in terms of its design (how it is built, how it works). Subjects include: neurobiological modeling, pception and associative memory, computational mental process (as those by Longuet-Higgins, H.C.).
|
|
課程要求 |
project, 作業, 測驗 上課 |
|
預期每週課後學習時數 |
|
|
Office Hours |
另約時間 備註： 預約 |
|
指定閱讀 |
http://red.csie.ntu.edu.tw/NN/index.php
+
http://red.csie.ntu.edu.tw/BT/index_eng.php |
|
參考書目 |
部分參考書目如下其餘甚多資料會email給修課同學：
[1] Unsupervised Learning, H.B. Barlow, Neural Computation 1, 295-311 (1989)
[2] Finding Minimum Entropy Codes, H.B. Barlow, T.P. Kaushal, G.J. Mitchison, Neural Computation 1, 412-423(1989)
[3] Nonlinear Dimensionality reduction by locally linear embedding, Sam T. Roweis and Lawrence K. Saul, Science, vol. 290. 22 December 2000, 2323-2326
[4] The manifold ways of perception, H. Sebastian Seung and Daniel D. Lee,
Science, vol 290, 22 December, 2268-2269
[5] Minimization of Boolean complexity in human concept learning
Jacob Feldman, Nature, vol 407, 5 October 2000, 630-632
[6] Reinforcement learning: An introduction, by R.S. Sutton and A.G. Barto, 1998, MIT Press.
|
|
評量方式
(僅供參考) |
|
|
週次 |
日期 |
單元主題 |
|
第2週 |
3/07 |
Hopfield model : introduction |
|
第3週 |
3/14 |
reinforcement learning : introduction |
|
第4週 |
3/21 |
NetTalk: introduction
https://pdfs.semanticscholar.org/b705/2570d4a8016f94eb788d921aa94b7724fecb.pdf
http://archive.ics.uci.edu/ml/index.php
|
|
第5週 |
3/28 |
self-organizing map
http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=28
http://concepts.psych.wisc.edu/papers/711/Kohonen90ProcIEEE.SOM.pdf
|
|
第6週 |
4/04 |
no class |
|
第7週 |
4/11 |
Boltzmann machine
https://pdfs.semanticscholar.org/a0d1/6f0e99f7ce5e6fb70b1a68c685e9ad610657.pdf |
|
第8週 |
4/18 |
Elman network
https://crl.ucsd.edu/~elman/Papers/fsit.pdf
https://pdfs.semanticscholar.org/59e4/0d166a46e14b37bc90041864eca26af6ae00.pdf
|
|
第9週 |
4/25 |
Elman network
https://pdfs.semanticscholar.org/59e4/0d166a46e14b37bc90041864eca26af6ae00.pdf
Segmentation of DNA Using Simple Recurrent Neural Network
https://www.sciencedirect.com/science/article/pii/S0950705111002024?via%3Dihub |
|
第10週 |
5/02 |
reinforcement learning
https://www.csie.ntu.edu.tw/~cyliou/red/NN/Demo/demo.html |
|
第11週 |
5/09 |
Chapter 1: Complexity of perceptron
Chapter 2: Training complexity of single perceptron
Chapter 3: Perfect classification of layered perceptrons
Chapters 1, 2, and 3 in
https://www.csie.ntu.edu.tw/~cyliou/red/NN/Classinfo/classinfo.html |
|
第12週 |
5/16 |
Chapter 4: Principle of multi-layer perceptron
https://www.csie.ntu.edu.tw/~cyliou/red/NN/Classinfo/classinfo.html |
|
第13週 |
5/23 |
Chapter 5
https://www.csie.ntu.edu.tw/~cyliou/red/NN/Classinfo/classinfo.html |
|
第14週 |
5/30 |
Hinton's deep learning |
|
第15週 |
6/06 |
Refined Hopfield model.
Chapter 6
https://www.csie.ntu.edu.tw/~cyliou/red/NN/Classinfo/classinfo.html |
|
第16週 |
6/13 |
Refined SOM. |
|
第17週 |
6/20 |
測驗考試 |
|
第18週 |
6/27 |
複習 (自由參加 非上課) |
|