计算学习.docVIP

计算学习(PAC,Leslie?Valiant)与统计学习(SVM,Vladimir?Vapnik) (2011-08-08 10:59:55) 标签： 校园 分类： 工作篇 因“对众多计算理论所做的变革性的贡献”而获奖  北京时间3月10日消息，据国外媒体报道，哈佛大学计算机科学家莱斯利·瓦伦特（Leslie Valiant）获2010年图灵奖，其研究课题广泛，涵盖了从人工智能到分布式计算等领域。 美国计算机协会（ACM）每年一度颁发的图灵奖被誉为“计算世界的诺贝尔奖”，奖金为25万美元，由Google和英特尔赞助。 美国计算机协会总裁阿兰·切斯奈斯（Alain Chesnais）发表声明称：“过去30年来，莱斯利·瓦伦特为人工智能进步提供了理论基础，在改进机器学习方面取得骄人成绩。他在计算科学和数学领域的远见及认知理论与其它技术结合后，开创了机器学习和通信的新时代，如IBM推出的计算系统已经能够挑战人类回答问题的能力。” 瓦伦特的影响作包括《学习理论》（Theory of the Learnable）论文，被认为是机器学习的鼻祖。在其理论基础上发展的新算法适用于网络传感器和数据库设备的环境反馈。更具体些，其理论催生出垃圾邮件过滤技术。 1982年，瓦伦特在《高速并行通信计划》（A Scheme for Fast Parallel Communication）论文中列出解决网络堵塞问题的解决方案。 最近，瓦伦特致力于计算神经科学的研究，并出版《大脑电路》（Circuits of the Mind）一书，使用计算方法研究人脑工作方式。 瓦伦特的研究工作还推动了自然语言处理、手写识别和计算机视觉领域的发展。 ? ? ? ? ? Leslie Gabriel Valiant (born 28 March 1949) is a British computer scientist and computational theorist[1]. He was educated at Kings College, Cambridge, Imperial College London, and University of Warwick where he received his Ph.D. in computer science in 1974. He started teaching at Harvard University in 1982 and is currently the T. Jefferson Coolidge Professor of Computer Science and Applied Mathematics in the Harvard School of Engineering and Applied Sciences. Prior to 1982 he taught at Carnegie Mellon University, Leeds University, and the University of Edinburgh. Valiant is world-renowned for his work in theoretical computer science. Among his many contributions to complexity theory, he introduced the notion of #P-completeness to explain why enumeration and reliability problems are intractable. He also introduced the probably approximately correct (PAC) model of machine learning that has helped the field of computational learning theory grow, and the concept of holographic algorithms. His earlier work in automata theory includes an algorithm for context-free parsing, which is (as of 2010) still the asymptotically fastest known. He also works in computational neuroscience focusing on understanding memory and learning. He received the Nevan