6.891 Machine Learning and Neural Networks

Related Info

EM
  • Pages from Bishop's Neural Networks for Pattern Recognition:
  • 1, 2, 3, 4, 5
    • Ockham's Razor
  • Encyclopedia Britannica has an obscure entry.
  • This description is much clearer.
    • Bayes Nets
  • The matlab Bayes Net Toolkit.
  • An brief associated tutorial.
  • The JavaBayes Demo software .
  • A local copy of JavaBayes .
  • A fantastic reference: "Inference in Belief Networks: A procedural guide".
  • Chapter 2 and Chapter 4 of Finn's Introduction to Bayes Nets book.
    • Face Detection
  • Sung and Poggio:
  • The paper: Example Based Learning for View-Based Human Face Detection
  • The web site: Face Detection
  • Rowley, Baluja, and Kanade:
  • Two papers:
  • Neural Network-Based Face Detection
  • Rotation Invariant Neural Network-Based Face Detection
  • The web site: Face Detection Project
  • The demo: CMU's Face Detector Demo
    • Support Vector Machines
  • Manual for SVM C programs here.
  • This is a good starting point.
  • Here is a reasonable tutorial.
  • The Lucent SVM web page.
  • Royal Holloway, University of London, Department of Computer Science also does work on SVM's.
  • Check out there nice web demo....
  • Some matlab code for SVM's here.
  • A ``Simple Learning Algorithms for Training Support Vector Machines'' by Campbell and Cristianini is a paper which describes a simple approach to finding perceptrons with large margin. Campbell's web page is here.
    • Numerical Recipes in C
  • This truly fantastic book is actually available on-line.
  • The chapter that describes linear programming is available here.
    • Independent Component Analysis
  • The paper on separating images by Hany Farid is here
  • Tony Bell has a good web page listing many of the important papers.
  • From that web site, the following are good starting points:
  • Bell A.J. and Sejnowski T.J. 1995. An information maximisation approach to blind separation and blind deconvolution, Neural Computation, 7, 6, 1129-1159 Abstract , Paper (0.9MB), Compressed (0.3MB) (38 pages). [3 short conference papers on the same material: ICASSP 95 (1.4MB, 4 pages) , NIPS 94 (0.2MB, 8 pages), and NOLTA95. ]
  • Pearlmutter B.A. and Parra L.C. 1996. A context-sensitive generalization of ICA, Proc. ICONIP '96, Japan Paper
  • John Fisher also has a page with his ICA papers including J. W. Fisher III, and J. C. Principe, Unsupervised learning for nonlinear synthetic discriminant functions, Proceeding of SPIE, vol. 2752, Orlando, April, 1996.
    • Boosting, Bagging, Etc.
  • The following reference is the best for beginning to read about boosting. Freund's homepage has an example applet.
  • Yoav Freund and Robert Schapire. A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences, 55(1):119-139, 1997.
  • Schapire also has a nice listing of more rescent papers and work on boosting.
  • If you like the word bagging more: Leo Breiman. Bagging Predictors. Tech-Report #421, September 1994. Department of Statistics, UCB.
    • Tangent Spaces and Mixtures of PCA
  • Trevor Hastie has a page listing a number of his papers (mostly from 1994) on these kinds of methods including:
  • Hastie, T. J., Simard, P. Y., and Saeckinger, E. "Learning Prototype Models for Tangent Distance." NIPS proceedings, 1994.
  • Other similar papers can be found at Chris Atkeson's page about local learning.
  • Efficient pattern recognition using a new transformation distance by P. Simard, Y. LeCun and J. Denker. In "Advances in Neural Information Processing Systems V", Morgan Kaufmann Publishers, pp. 50--58, 1993. is also a nice article. I have a copy in my office if you'd like to photocopy it.
  • Tipping M. E. and Bishop C. M. Mixtures of Probabilistic Principal Component Analysers Tech-report NCRG/97/003, June 11, 1997. is also a nice paper on a similar technique.
    • Paul A. Viola
    Last modified: Sun Nov 28 13:51:36 EST 1999