Agnostic PAC Learning of Functions on Analog Neural Nets
暂无分享,去创建一个
[1] J. Milnor. On the Betti numbers of real varieties , 1964 .
[2] John E. Savage,et al. The Complexity of Computing , 1976 .
[3] Kenneth Steiglitz,et al. Combinatorial Optimization: Algorithms and Complexity , 1981 .
[4] Leslie G. Valiant,et al. A theory of the learnable , 1984, STOC '84.
[5] D. E. Rumelhart,et al. chapter Parallel Distributed Processing, Exploration in the Microstructure of Cognition , 1986 .
[6] Richard P. Lippmann,et al. An introduction to computing with neural nets , 1987 .
[7] Ronald L. Rivest,et al. Training a 3-node neural network is NP-complete , 1988, COLT '88.
[8] David Haussler,et al. Equivalence of models for polynomial learnability , 1988, COLT '88.
[9] M. Kearns,et al. Crytographic limitations on learning Boolean formulae and finite automata , 1989, STOC '89.
[10] J. Renegar,et al. On the Computational Complexity and Geometry of the First-Order Theory of the Reals, Part I , 1989 .
[11] David Haussler,et al. What Size Net Gives Valid Generalization? , 1989, Neural Computation.
[12] David Haussler,et al. Learnability and the Vapnik-Chervonenkis dimension , 1989, JACM.
[13] J. Stephen Judd,et al. Neural network design and the complexity of learning , 1990, Neural network modeling and connectionism.
[14] D. Pollard. Empirical Processes: Theory and Applications , 1990 .
[15] Ronald L. Rivest,et al. Training a 3-node neural network is NP-complete , 1988, COLT '88.
[16] Linda Sellie,et al. Toward efficient agnostic learning , 1992, COLT '92.
[17] James Renegar,et al. On the Computational Complexity and Geometry of the First-Order Theory of the Reals, Part I: Introduction. Preliminaries. The Geometry of Semi-Algebraic Sets. The Decision Problem for the Existential Theory of the Reals , 1992, J. Symb. Comput..
[18] David Haussler,et al. Decision Theoretic Generalizations of the PAC Model for Neural Net and Other Learning Applications , 1992, Inf. Comput..
[19] Paul W. Goldberg,et al. Bounding the Vapnik-Chervonenkis Dimension of Concept Classes Parameterized by Real Numbers , 1993, COLT '93.
[20] Wolfgang Maass,et al. Bounds for the computational power and learning complexity of analog neural nets , 1993, SIAM J. Comput..
[21] Leslie G. Valiant,et al. Cryptographic Limitations on Learning Boolean Formulae and Finite Automata , 1993, Machine Learning: From Theory to Applications.
[22] Wolfgang Maass,et al. Computing on Analog Neural Nets with Arbitrary Real Weights , 1994 .
[23] Wolfgang Maass,et al. Perspectives of Current Research about the Complexity of Learning on Neural Nets , 1994 .
[24] Robert E. Schapire,et al. Efficient distribution-free learning of probabilistic concepts , 1990, Proceedings [1990] 31st Annual Symposium on Foundations of Computer Science.