论文信息 - Learning Translation Invariant Recognition in Massively Parallel Networks

Learning Translation Invariant Recognition in Massively Parallel Networks

One major goal of research on massively parallel networks of neuron-like processing elements is to discover efficient methods for recognizing patterns. Another goal is to discover general learning procedures that allow networks to construct the internal representations that are required for complex tasks. This paper describes a recently developed procedure that can learn to perform a recognition task. The network is trained on examples in which the input vector represents an instance of a pattern in a particular position and the required output vector represents its name. After prolonged training, the network develops canonical internal representations of the patterns and it uses these canonical representations to identify familiar patterns in novel positions.

Geoffrey E. Hinton

[1] A. A. Mullin,et al. Principles of neurodynamics , 1962 .

[2] Roger K. Moore. Computer Speech and Language , 1986 .

[3] Geoffrey E. Hinton,et al. Experiments on Learning by Back Propagation. , 1986 .

[4] Jerome A. Feldman,et al. Connectionist Models and Their Properties , 1982, Cogn. Sci..

[5] Geoffrey E. Hinton,et al. Learning representations by back-propagating errors , 1986, Nature.

[6] Geoffrey E. Hinton,et al. Parallel Models of Associative Memory , 1989 .

[7] Geoffrey E. Hinton,et al. A Learning Algorithm for Boltzmann Machines , 1985, Cogn. Sci..

[8] James L. McClelland,et al. Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[9] D. E. Rumelhart,et al. Learning internal representations by back-propagating errors , 1986 .

[10] Geoffrey E. Hinton,et al. Learning sets of filters using back-propagation , 1987 .

[11] Geoffrey E. Hinton,et al. Learning internal representations by error propagation , 1986 .

[12] Eric Saund. Abstraction and Representation of Continuous Variables in Connectionist Networks , 1986, AAAI.

[13] Allen Newell,et al. Physical Symbol Systems , 1980, Cogn. Sci..

[14] Paul Losleben. Advanced research in VLSI : proceedings of the 1987 Stanford Conference , 1987 .

[15] Terrence J. Sejnowski,et al. NETtalk: a parallel network that learns to read aloud , 1988 .