### Abstract

A multilayer perceptron is a feedforward artificial neural network model that maps sets of input data onto a set of appropriate output. It is a modification of the standard linear perceptron in that it uses three or more layers of neurons (nodes) with nonlinear activation functions, and is more powerful than the perceptron in that it can distinguish data that is not linearly separable, or separable by a hyper plane. MLP networks are general-purpose, flexible, nonlinear models consisting of a number of units organised into multiple layers. The complexity of the MLP network can be changed by varying the number of layers and the number of units in each layer. Given enough hidden units and enough data, it has been shown that MLPs can approximate virtually any function to any desired accuracy. This paper presents the performance comparison between Multi-layer Perceptron (Back Propagation, Delta Rule and Perceptron). Perceptron is a steepest descent type algorithm that normally has slow convergence rate and the search for the global minimum often becomes trapped at poor local minima. The current study investigates the performance of three algorithms to train MLP networks. Its was found that the Perceptron algorithm are much better than others algorithms.

Original language | English |
---|---|

Title of host publication | 2009 IEEE International Advance Computing Conference, IACC 2009 |

Pages | 296-299 |

Number of pages | 4 |

DOIs | |

Publication status | Published - 2009 |

Event | 2009 IEEE International Advance Computing Conference, IACC 2009 - Patiala Duration: 6 Mar 2009 → 7 Mar 2009 |

### Other

Other | 2009 IEEE International Advance Computing Conference, IACC 2009 |
---|---|

City | Patiala |

Period | 6/3/09 → 7/3/09 |

### Fingerprint

### Keywords

- Backpropagation
- Classification
- Delta rule learning
- Perceptron

### ASJC Scopus subject areas

- Software
- Electrical and Electronic Engineering

### Cite this

*2009 IEEE International Advance Computing Conference, IACC 2009*(pp. 296-299). [4809024] https://doi.org/10.1109/IADCC.2009.4809024

**Performance comparison of multi-layer perceptron (Back Propagation, Delta Rule and Perceptron) algorithms in neural networks.** / Alsmadi, Mutasem Khalil; Omar, Khairuddin; Mohd Noah, Shahrul Azman; Almarashdah, Ibrahim.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

*2009 IEEE International Advance Computing Conference, IACC 2009.*, 4809024, pp. 296-299, 2009 IEEE International Advance Computing Conference, IACC 2009, Patiala, 6/3/09. https://doi.org/10.1109/IADCC.2009.4809024

}

TY - GEN

T1 - Performance comparison of multi-layer perceptron (Back Propagation, Delta Rule and Perceptron) algorithms in neural networks

AU - Alsmadi, Mutasem Khalil

AU - Omar, Khairuddin

AU - Mohd Noah, Shahrul Azman

AU - Almarashdah, Ibrahim

PY - 2009

Y1 - 2009

N2 - A multilayer perceptron is a feedforward artificial neural network model that maps sets of input data onto a set of appropriate output. It is a modification of the standard linear perceptron in that it uses three or more layers of neurons (nodes) with nonlinear activation functions, and is more powerful than the perceptron in that it can distinguish data that is not linearly separable, or separable by a hyper plane. MLP networks are general-purpose, flexible, nonlinear models consisting of a number of units organised into multiple layers. The complexity of the MLP network can be changed by varying the number of layers and the number of units in each layer. Given enough hidden units and enough data, it has been shown that MLPs can approximate virtually any function to any desired accuracy. This paper presents the performance comparison between Multi-layer Perceptron (Back Propagation, Delta Rule and Perceptron). Perceptron is a steepest descent type algorithm that normally has slow convergence rate and the search for the global minimum often becomes trapped at poor local minima. The current study investigates the performance of three algorithms to train MLP networks. Its was found that the Perceptron algorithm are much better than others algorithms.

AB - A multilayer perceptron is a feedforward artificial neural network model that maps sets of input data onto a set of appropriate output. It is a modification of the standard linear perceptron in that it uses three or more layers of neurons (nodes) with nonlinear activation functions, and is more powerful than the perceptron in that it can distinguish data that is not linearly separable, or separable by a hyper plane. MLP networks are general-purpose, flexible, nonlinear models consisting of a number of units organised into multiple layers. The complexity of the MLP network can be changed by varying the number of layers and the number of units in each layer. Given enough hidden units and enough data, it has been shown that MLPs can approximate virtually any function to any desired accuracy. This paper presents the performance comparison between Multi-layer Perceptron (Back Propagation, Delta Rule and Perceptron). Perceptron is a steepest descent type algorithm that normally has slow convergence rate and the search for the global minimum often becomes trapped at poor local minima. The current study investigates the performance of three algorithms to train MLP networks. Its was found that the Perceptron algorithm are much better than others algorithms.

KW - Backpropagation

KW - Classification

KW - Delta rule learning

KW - Perceptron

UR - http://www.scopus.com/inward/record.url?scp=66349096618&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=66349096618&partnerID=8YFLogxK

U2 - 10.1109/IADCC.2009.4809024

DO - 10.1109/IADCC.2009.4809024

M3 - Conference contribution

AN - SCOPUS:66349096618

SN - 9781424429288

SP - 296

EP - 299

BT - 2009 IEEE International Advance Computing Conference, IACC 2009

ER -