论文信息 - Reverse TDNN: An Architecture For Trajectory Generation

Reverse TDNN: An Architecture For Trajectory Generation

The backpropagation algorithm can be used for both recognition and generation of time trajectories. When used as a recognizer, it has been shown that the performance of a network can be greatly improved by adding structure to the architecture. The same is true in trajectory generation. In particular a new architecture corresponding to a "reversed" TDNN is proposed. Results show dramatic improvement of performance in the generation of hand-written characters. A combination of TDNN and reversed TDNN for compact encoding is also suggested.

Yann LeCun | Patrice Y. Simard | Yann LeCun | P. Simard

[1] Yann Le Cun,et al. A Theoretical Framework for Back-Propagation , 1988 .

[2] Barak A. Pearlmutter. Learning state space trajectories in recurrent neural networks : a preliminary report. , 1988 .

[3] Yann LeCun,et al. Generalization and network design strategies , 1989 .

[4] Barak A. Pearlmutter. Learning State Space Trajectories in Recurrent Neural Networks , 1989, Neural Computation.

[5] Lawrence D. Jackel,et al. Handwritten Digit Recognition with a Back-Propagation Network , 1989, NIPS.

[6] Lawrence D. Jackel,et al. Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

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

[8] Kevin J. Lang. A time delay neural network architecture for speech recognition , 1989 .

[9] Françoise Fogelman-Soulié,et al. Speaker-independent isolated digit recognition: Multilayer perceptrons vs. Dynamic time warping , 1990, Neural Networks.

[10] Isabelle Guyon,et al. Design of a neural network character recognizer for a touch terminal , 1991, Pattern Recognit..