Learning Systems Group

Publications

2002

• M. Magdon-Ismail, H.-C. Chen, and Y. S. Abu-Mostafa.
  The Multilevel Classification Problem and a Monotonicity Hint.
  In H. Yin, et al., eds., Intelligent Data Engineering and Automated Learning -- IDEAL 2002, vol. 2412 of Lecture Notes in Computer Science, pp. 410-415. Springer-Verlag, Berlin, 2002.
  abstract, PDF
• L. Li, A. Martinoli, and Y. S. Abu-Mostafa.
  Emergent Specialization in Swarm Systems.
  In H. Yin, et al., eds., Intelligent Data Engineering and Automated Learning -- IDEAL 2002, vol. 2412 of Lecture Notes in Computer Science, pp. 261-266. Springer-Verlag, Berlin, 2002.
  abstract, PDF, PS, PS.GZ.
• L. Li.
  Distributed Learning in Swarm Systems: A Case Study.
  M.S. Thesis, California Institute of Techology, May 2002.
  abstract, PDF, PS, PS.GZ.
• A. Nicholson.
  Generalization Error Estimates and Training Data Valuation.
  Ph.D. Thesis, California Institute of Technology, May 2002.
  Thesis available upon request.

2001

• Y. S. Abu-Mostafa.
  Financial model calibration using consistency hints.
  IEEE Trans. on Neural Networks, 12(4):791-808, July 2001.
  PS.GZ.

2000

• A. Nicholson.
  Evolution and Learning for Digital Circuit Design.
  In GECCO-2000: Proceedings of the Genetic and Evolutionary Computation Conference, San Francisco: Morgan Kaufmann, pp.519-524, 2000.
  postscript.
• A. Nicholson.
  A Generalization Model and Learning in Hardware.
  CSTR 2000.007, Caltech, 2000.
  abstract, postscript.

1999

• Z. Cataltepe, Y. S. Abu-Mostafa, and M. Magdon-Ismail.
  No Free Lunch for Early Stopping.
  Neural Computation, 11(4):995-1009, May 1999.
  PDF.

1998

• Z. Cataltepe.
  Incorporating Input Information into Learning and Augmented Objective Functions.
  Ph.D. Thesis, California Institute of Techology.
  abstract, thesis available upon request.
• M. Magdon-Ismail.
  Supervised Learning in Probabilistic Environments.
  Ph.D. Thesis, California Institute of Technology.
  abstract, thesis available upon request.
• M. Magdon-Ismail, A. Nicholson and Y.S. Abu-Mostafa.
  Estimating Model Limitation in Financial Markets.
  In Intelligent Data Engineering and Learning (IDEAL98) (Xu,Chan,King,Fu eds.), Hong Kong: Springer, pp.19-26,1998.
  postscript.
• M. Magdon-Ismail, A. Nicholson and Y.S. Abu-Mostafa.
  Financial Markets: Very Noisy Information Processing.
  Proceedings of the IEEE Special Issue on Information Processing, 86:2184-2195,1998.
  postscript.
• M. Magdon-Ismail and Y. S. Abu-Mostafa.
  Validation of Volatility Models.
  Journal of Forecasting.
  abstract, postscript.
• M. Magdon-Ismail and A. F. Atiya.
  Neural Networks for Density Estimation.
  Advances in Neural Information Processing Systems (NIPS), 11:522-528, 1998.
  postscript.
• J. Sill.
  The Capacity of Monotonic Functions.
  Discrete Applied Mathematics (special issue on VC dimension), vol 86, 95-107, 1998.
  abstract, postscript.
• J. Sill.
  Monotonic Networks.
  Advances in Neural Information Processing Systems, vol 10, 661-667, 1998.
  abstract, postscript.

1997

• E. Bax, Z. Cataltepe and J. Sill.
  The Central Classifier Bound -- A New Error Bound for the Classifier Chosen by Early Stopping.
  IEEE PACRIM, Victoria, B.C. 1997 conference proceedings.
  postscript (322K).
  (also available as Caltech-CS-TR-97-08)
• Z. Cataltepe and M. Magdon-Ismail.
  Incorporating Test Inputs into Learning.
  Proceedings of the Advances in Neural Information Processing Systems 10 .
  abstract, postscript (194K).
• R. A. Sahan, D. C. Albin, N. K. Sahan and Z. Cataltepe.
  Modelling Of Transitional Air Flow System In A Channel Using Artificial Neural Networks.
  Sixth Turkish Symposium on Artificial Intelligence and Neural Networks ( TAINN 97 ).
• J. Sill and Y. S. Abu-Mostafa.
  Monotonicity Hints.
  Advances in Neural Information Processing Systems, vol 9, 634-640, 1997.
  abstract, postscript.

1996

• M. Magdon-Ismail and Y. S. Abu-Mostafa.
  Systematic Underprediction of Volatility in Maximum Likelihood Methods.
  NNCM '96.
  abstract, postscript (194K).

1994

• Z. Cataltepe and Y. S. Abu-Mostafa.
  Estimating Learning Performance Using Hints.
  Proceedings of the 1993 Connectionist Models Summer School, M. Mozer et. al. (Eds.), Lawrence Erlbaum Associates, Publishers, Hillsdale, NJ. pp.380-386.
  abstract, postscript (433K).
• Z. Cataltepe.
  The Scheduling Problem in Learning from Hints.
  M.S. Thesis, California Institute of Techology.
  abstract, postscript (675K).
  (also available as Caltech-CS-TR-94-09)