### Abstract

A discussion on the representational abilities of Single Layer Recurrent Neural Networks (SLRNNs) is presented. The fact that SLRNNs can not implement all finite-state recognizers is addressed. However, there are methods that can be used to expand the representational abilities of SLRNNs, and some of these are explained. We will call such systems augmented SLRNNs. Some possibilities for augmented SLRNNs are: adding a layer of feedforward neurons to the SLRNN, allowing the SLRNN to have an extra time step to calculate the solution, and increasing the order of the SLRNN. It is significant that, for some problems, some augmented SLRNNs must actually implement a non-minimal finite-state recognizer that is equivalent to the desired finite-state recognizer. Simulations are performed that demonstrate the use of both a SLRNN and an augmented SLRNN for the problem of learning an odd parity finite-state recognizer using a gradient descent method.

Original language | English (US) |
---|---|

Pages (from-to) | 51-54 |

Number of pages | 4 |

Journal | IEE Conference Publication |

Issue number | 372 |

State | Published - 1993 |

### Fingerprint

### All Science Journal Classification (ASJC) codes

- Electrical and Electronic Engineering

### Cite this

*IEE Conference Publication*, (372), 51-54.

}

*IEE Conference Publication*, no. 372, pp. 51-54.

**On recurrent neural networks and representing finite-state recognizers.** / Goudreau, M. W.; Giles, C. L.

Research output: Contribution to journal › Article

TY - JOUR

T1 - On recurrent neural networks and representing finite-state recognizers

AU - Goudreau, M. W.

AU - Giles, C. L.

PY - 1993

Y1 - 1993

N2 - A discussion on the representational abilities of Single Layer Recurrent Neural Networks (SLRNNs) is presented. The fact that SLRNNs can not implement all finite-state recognizers is addressed. However, there are methods that can be used to expand the representational abilities of SLRNNs, and some of these are explained. We will call such systems augmented SLRNNs. Some possibilities for augmented SLRNNs are: adding a layer of feedforward neurons to the SLRNN, allowing the SLRNN to have an extra time step to calculate the solution, and increasing the order of the SLRNN. It is significant that, for some problems, some augmented SLRNNs must actually implement a non-minimal finite-state recognizer that is equivalent to the desired finite-state recognizer. Simulations are performed that demonstrate the use of both a SLRNN and an augmented SLRNN for the problem of learning an odd parity finite-state recognizer using a gradient descent method.

AB - A discussion on the representational abilities of Single Layer Recurrent Neural Networks (SLRNNs) is presented. The fact that SLRNNs can not implement all finite-state recognizers is addressed. However, there are methods that can be used to expand the representational abilities of SLRNNs, and some of these are explained. We will call such systems augmented SLRNNs. Some possibilities for augmented SLRNNs are: adding a layer of feedforward neurons to the SLRNN, allowing the SLRNN to have an extra time step to calculate the solution, and increasing the order of the SLRNN. It is significant that, for some problems, some augmented SLRNNs must actually implement a non-minimal finite-state recognizer that is equivalent to the desired finite-state recognizer. Simulations are performed that demonstrate the use of both a SLRNN and an augmented SLRNN for the problem of learning an odd parity finite-state recognizer using a gradient descent method.

UR - http://www.scopus.com/inward/record.url?scp=0027235145&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027235145&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0027235145

SP - 51

EP - 54

JO - IEEE Conference Publication

JF - IEEE Conference Publication

SN - 0537-9989

IS - 372

ER -