ML Anthology

FIR and IIR Synapses, a New Neural Network Architecture for Time Series Modeling

Andrew D. Back, Ah Chung Tsoi
NeCo 1991 pp. 375-385
doi:10.1162/NECO.1991.3.3.375 /neco/1991/back1991neco-fir/

Abstract

A new neural network architecture involving either local feedforward global feedforward, and/or local recurrent global feedforward structure is proposed. A learning rule minimizing a mean square error criterion is derived. The performance of this algorithm (local recurrent global feedforward architecture) is compared with a local-feedforward global-feedforward architecture. It is shown that the local-recurrent global-feedforward model performs better than the local-feedforward global-feedforward model.

NeCo Semantic Scholar

Cite

Text

Back and Tsoi. "FIR and IIR Synapses, a New Neural Network Architecture for Time Series Modeling." Neural Computation, 1991. doi:10.1162/NECO.1991.3.3.375

Markdown

[Back and Tsoi. "FIR and IIR Synapses, a New Neural Network Architecture for Time Series Modeling." Neural Computation, 1991.](https://mlanthology.org/neco/1991/back1991neco-fir/) doi:10.1162/NECO.1991.3.3.375

BibTeX

@article{back1991neco-fir,
  title     = {{FIR and IIR Synapses, a New Neural Network Architecture for Time Series Modeling}},
  author    = {Back, Andrew D. and Tsoi, Ah Chung},
  journal   = {Neural Computation},
  year      = {1991},
  pages     = {375-385},
  doi       = {10.1162/NECO.1991.3.3.375},
  volume    = {3},
  url       = {https://mlanthology.org/neco/1991/back1991neco-fir/}
}