Difference between revisions of "VS298: Reading"

From RedwoodCenter
Jump to navigationJump to search
(2 intermediate revisions by the same user not shown)
Line 25: Line 25:
 
* Y. LeCun, L. Bottou, G. Orr, and K. Muller (1998) [http://connes.berkeley.edu/~amir/vs298/lecun-98b.pdf  "Efficient BackProp,"]  in Neural Networks: Tricks of the trade, (G. Orr and Muller K., eds.).
 
* Y. LeCun, L. Bottou, G. Orr, and K. Muller (1998) [http://connes.berkeley.edu/~amir/vs298/lecun-98b.pdf  "Efficient BackProp,"]  in Neural Networks: Tricks of the trade, (G. Orr and Muller K., eds.).
 
* [http://www.cnl.salk.edu/ParallelNetsPronounce/index.php NetTalk demo]
 
* [http://www.cnl.salk.edu/ParallelNetsPronounce/index.php NetTalk demo]
 +
 +
==== 23 Sep ====
 +
* Handout: [http://connes.berkeley.edu/~amir/vs298/hebb-pca.pdf Hebbian learning and PCA]
 +
* '''HKP''' Chapter 8
 +
* '''PDP''' [http://connes.berkeley.edu/~amir/vs298/chap9.pdf Chapter 9] (full text of Michael Jordan's tutorial on linear algebra, including section on eigenvectors)
 +
 +
==== 30 Sep ====
 +
* Foldiak, P. [http://connes.berkeley.edu/~amir/vs298/foldiak90.pdf Forming sparse representations by local anti-Hebbian learning]. Biol. Cybern. 64, 165-170 (1990).
 +
* '''HKP''' Chapter 9
 +
* Olshausen BA, Field DJ Emergence of simple-cell receptive field properties by learning a sparse code for natural images, Nature, 381: 607-609. (1996)

Revision as of 17:57, 2 October 2008

For each lecture, we also have a list of optional reading corresponding to ideas discussed in lecture. You may read these if you are interested in the particular topic: Optional Reading

2 Sep

04 Sep

Optional reading for more background:

16 Sep

  • Handout on supervised learning in single-stage feedforward networks

18 Sep

  • Handout on supervised learning in multi-layer feedforward networks - "backpropagation"
  • Y. LeCun, L. Bottou, G. Orr, and K. Muller (1998) "Efficient BackProp," in Neural Networks: Tricks of the trade, (G. Orr and Muller K., eds.).
  • NetTalk demo

23 Sep

30 Sep