Yaser S. Abu-Mostafa

Ph.D., Electrical Engineering, California Institute of Technology, 1983;
M.S, Electrical Engineering, Georgia Institute of Technology, 1981;
B.S., Cairo University, 1979.

Yaser S. Abu-Mostafa is a Professor of Electrical Engineering and Computer Science and a member of the Computation and Neural Systems faculty at the California Institute of Technology.

Dr. Abu-Mostafa received the Clauser Prize for the most original doctoral thesis at Caltech. He received the ASCIT Teaching Awards in 1986, 1989 and 1991, the GSC Teaching Awards in 1995 and 2002, and the Richard P. Feynman prize for excellence in teaching in 1996. He was the founding Program Chairman of the annual IEEE Conference on Neural Information Processing Systems (NIPS) in Denver, and a founding member of the IEEE Neural Networks Council. He chaired the second and fourth international conferences on Neural Networks in the Capital Markets (NNCM-94 and NNCM-96), and the sixth international conference on Computational Finance (CF-99). He has served on the boards of several journals including the IEEE Transactions on Information Theory, the IEEE Transactions on Circuits and Systems, the Neural Networks Journal, the Journal of Complexity, Neurocomputing, and Neural Processing Letters. He also received the Kuwait State Award in Applied Science on Nov. 29, 1999. In 2005, The Hertz Foundation established a perpetual graduate fellowship named the Abu-Mostafa Fellowship in his honor.

Dr. Abu-Mostafa has more than 60 publications in the areas of learning theory, neural networks, pattern recognition, information theory, and computational finance, including two articles in Scientific American.

Research Interests

• Computational finance
• Learning from examples and hints
• Machine learning
• Neural networks
• Statistical learning theory

Selected Publications

See full publication list.

• Financial model calibration using consistency hints. Y. S. Abu-Mostafa. IEEE Trans. on Neural Networks, 12(4):791–808, July 2001. (ps.gz)
• No Free Lunch for Early Stopping. Z. Cataltepe, Y. S. Abu-Mostafa, and M. Magdon-Ismail. Neural Computation, 11(4):995–1009, May 1999. (pdf)
• Financial Markets: Very Noisy Information Processing. M. Magdon-Ismail, A. Nicholson and Y. S. Abu-Mostafa. Proceedings of the IEEE, 86(11):2184–2195, Nov. 1998. (pdf, ps)
• Validation of Volatility Models. M. Magdon-Ismail and Y. S. Abu-Mostafa. Journal of Forecasting, 17:349–368, Sep.-Nov. 1998. (ps)
• Introduction to Financial Forecasting. Y. S. Abu-Mostafa and A. Atiya. Applied Intelligence, 6(3):205–213, Jul. 1996.
• Hints. Y. S. Abu-Mostafa. Neural Computation, 7:639–671, July 1995. (ps)
• Machines That Learn from Hints. Y. S. Abu-Mostafa. Scientific American, 272(4):64–69, Apr. 1995.
• Hints and the VC Dimension. Y. S. Abu-Mostafa. Neural Computation, 5:278–288, MIT Press, March 1993.
• Learning from Hints in Neural Networks. Y. S. Abu-Mostafa. Journal of complexity, 6:192–198, Jun. 1990.
• The Vapnik-Chervonenkis Dimension: Information versus Complexity in Learning. Y. S. Abu-Mostafa. Neural Computation, 1:312–317, MIT Press, 1989.
• Information Capacity of the Hopfield Model. Y. S. Abu-Mostafa and J. St. Jaques. IEEE Trans. on Information Theory, IT-32:513–525, Jul. 1986.
• Recognitive Aspects of Moment Invariants. Y. S. Abu-Mostafa and D. Psaltis. IEEE Trans. on Pattern Analysis and Machine Intelligence, PAMI-6:698–706, Nov. 1984.