论文信息 - Representation and Induction of Finite State Machines using Time-Delay Neural Networks

Representation and Induction of Finite State Machines using Time-Delay Neural Networks

This work investigates the representational and inductive capabilities of time-delay neural networks (TDNNs) in general, and of two subclasses of TDNN, those with delays only on the inputs (IDNN), and those which include delays on hidden units (HDNN). Both architectures are capable of representing the same class of languages, the definite memory machine (DMM) languages, but the delays on the hidden units in the HDNN helps it outperform the IDNN on problems composed of repeated features over short time windows.

[1] Don R. Hush,et al. On the node complexity of neural networks , 1994, Neural Networks.

[2] Eric A. Wan,et al. Time series prediction by using a connectionist network with internal delay lines , 1993 .

[3] J. Rice. Mathematical Statistics and Data Analysis , 1988 .

[4] Geoffrey E. Hinton,et al. Phoneme recognition using time-delay neural networks , 1989, IEEE Trans. Acoust. Speech Signal Process..

[5] Edward A. Feigenbaum,et al. Switching and Finite Automata Theory: Computer Science Series , 1990 .

[6] Andreas S. Weigend,et al. Time Series Prediction: Forecasting the Future and Understanding the Past , 1994 .

[7] Geoffrey E. Hinton,et al. A time-delay neural network architecture for isolated word recognition , 1990, Neural Networks.