ACM称,Valiant在机器学习,计算复杂度理论,并行和分布式计算等领域都有突出贡献,推动了人工智能技术的发展。在Valiant之前,有很多人在研究机器学习,也取得了不俗的贡献,但一个基础问题始终没有攻破——如何处理错误。当时的机器学习能执行阳性结果和阴性结果,对超过样本局限之外的情况无法自我发挥,系统无法处理不可避免的错误。Valiant在1984年提出了概率近似正确模型,以一种弱学习方式训练机器学习,输入的信息越充分它的预测也会愈加精确,它允许未来的错误发生,比如我们所熟悉的垃圾邮件过滤器。在复杂度理论方面,Valiant提出了复杂度#P完全概念。 Leslie Valiant Contact Info: Office Hours: Thursdays 1.30-2.30 pm. Recent Publications: 71. Circuits of the Mind, Oxford University Press, (1994, 2000). 72. Robust logics, Artificial Intelligence Journal, 117 (2000) 231-253. 73. A neuroidal architecture for cognitive computation, J. Assoc. Computing Machinery, 47:5 (2000) 854-882. 74. Quantum circuits that can be simulated classically in polynomial time, SIAM J. on Computing, 31:4 (2002) 1229-1254. 75. Expressiveness of matchgates, Theoretical Computer Science, 289:1 (2002) 457-471 (and 299 (2003) 795.) 76. Three problems in computer science, J. Assoc. Computing Machinery, 50:1 (2003) 96-99. 77. Holographic algorithms (extended abstract), Proc. 45th Annual IEEE Symposium on Foundations of Computer Science, Oct 17-19, Rome, Italy, (2004). IEEE Press, 306-315. 78. Memorization and association on a realistic neural model, Neural Computation, 17:3 (2005) 527-555. 79. Holographic circuits, Proc. 32nd International Colloquium on Automata, Languages and Programming, July 11-15, Lisbon, Portugal, LNCS, Vol. 3580, (2005), Springer-Verlag, 1-15. 80. Completeness for parity problems, Proc. 11th International Computing and Combinatorics Conference, Aug 16-19, Kunming, China, LNCS, Vol. 3959, (2005), Springer-Verlag, 1-9. 81. A quantitative theory of neural computation, Biological Cybernetics, 95:3 (2006) 205-211. 82. Knowledge infusion, Proc. 21st National Conference on Artificial Intelligence, AAAI06, Jul 16-20, Boston, MA, AAAI Press, (2006), 1546-1551. 83. Accidental algorithms, Proc. 47th Annual IEEE Symposium on Foundations of Computer Science, Oct 22 -24, Berkeley, CA, IEEE Press, (2006), 509-517. 84. Holographic algorithms, SIAM J. on Computing, 37:5 (2008) 1565-1594. (Earlier version: Electronic Colloquium on Computational Complexity, Report TR05-099, (2005).) 85. A first experimental demonstration of massive knowledge infusion, (with Loizos Michael), Proc. 11th International Conference on Principles of Knowledge Representation and Reasoning, Sept. 16-20, 2008, Sydney, Australia, 378-389. 86. Knowledge infusion: In pursuit of robustness in artificial intelligence, Proc 28th Conference on Foundations of Software Technology and Theoretical Computer Science, Dec 9-11, 2008, Bangalore, India, Indian Association for Research in Computing Science, 415-422. 87. Evolvability, J. Assoc. Computing Machinery, 56:1 (2009) 3:1 - 3:21. (Earlier version: Proc. 32nd International Symposium on Mathematical Foundations of Computer Science, Aug. 26-31, ?esky Krumlov, Czech Republic, LNCS, Vol 4708, (2007) Springer-Verlag, 22-43.) 88. Experience-induced neural circuits that achieve high capacity, (with Vitaly Feldman), Neural Computation, 21:10 (2009) 2715-2754. 89. A bridging model for multi-core computing, Journal of Computer and System Sciences, 77:1 (2011) 154-166 . (Earlier version: Proc. 16th Annual European Symposium on Algorithms, Sept. 15-17, 2008, Karlsruhe, Germany, LNCS, Vol 5193, (2008), Springer-Verlag, 13-28.) 90. Some observations on holographic algorithms, Proc. 9th Latin American Theoretical Informatics Symposium, LATIN 2010: Oaxaca, Mexico, April 19-23, 2010, LNCS, Vol 6034 Springer-Verlag (2010), 577-590. 91. Evolution with drifting targets, (with Varun Kanade and Jennifer Wortman Vaughan), Proc, 23rd Annual Conference on Learning Theory, (COLT 2010). This profile was referenced from: http://people.seas./~valiant/
|
|