|
Evolvability (computer Science)
The term evolvability is used for a recent framework of computational learning introduced by Leslie Valiant in his paper of the same name and described below. The aim of this theory is to model biological evolution and categorize which types of mechanisms are evolvable. Evolution is an extension of PAC learning and learning from statistical queries. General framework Let F_n\, and R_n\, be collections of functions on n\, variables. Given an ''ideal function'' f \in F_n, the goal is to find by local search a ''representation'' r \in R_n that closely approximates f\,. This closeness is measured by the ''performance'' \operatorname(f,r) of r\, with respect to f\,. As is the case in the biological world, there is a difference between genotype and phenotype. In general, there can be multiple representations (genotypes) that correspond to the same function (phenotype). That is, for some r,r' \in R_n, with r \neq r'\,, still r(x) = r'(x)\, for all x \in X_n. However, this need not be t ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Leslie Valiant
Leslie Gabriel Valiant (born 28 March 1949) is a British American computer scientist and computational theorist. He was born to a chemical engineer father and a translator mother. He is currently the T. Jefferson Coolidge Professor of Computer Science and Applied Mathematics at Harvard University. Valiant was awarded the Turing Award in 2010, having been described by the A.C.M. as a heroic figure in theoretical computer science and a role model for his courage and creativity in addressing some of the deepest unsolved problems in science; in particular for his "striking combination of depth and breadth". Education Valiant was educated at King's College, Cambridge, Imperial College London, and the University of Warwick where he received a PhD in computer science in 1974. Research and career 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 ("sharp-P comple ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Probably Approximately Correct Learning
In computational learning theory, probably approximately correct (PAC) learning is a framework for mathematical analysis of machine learning. It was proposed in 1984 by Leslie Valiant.L. Valiant. A theory of the learnable.' Communications of the ACM, 27, 1984. In this framework, the learner receives samples and must select a generalization function (called the ''hypothesis'') from a certain class of possible functions. The goal is that, with high probability (the "probably" part), the selected function will have low generalization error (the "approximately correct" part). The learner must be able to learn the concept given any arbitrary approximation ratio, probability of success, or distribution of the samples. The model was later extended to treat noise (misclassified samples). An important innovation of the PAC framework is the introduction of computational complexity theory concepts to machine learning. In particular, the learner is expected to find efficient functions (tim ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |