The search functionality is under construction.

The search functionality is under construction.

Multilayer feedforward neural network (MFNN) trained by the backpropagation (BP) algorithm is one of the most significant models in artificial neural networks. MFNNs have been used in many areas of signal and image processing due to high applicability. Although they have been implemented as analog, mixed analog-digital and fully digital VLSI circuits, it is still difficult to realize their hardware implementation with the BP learning function efficiently. This paper describes a special BP algorithm for the logic oriented neural network (LOGO-NN) which we have proposed as a sort of MFNN with quantized weights and multilevel threshold neurons. Both weights and neuron outputs are quantized to integer values in LOGO-NNs. Furthermore, the proposed BP algorithm can reduce high precise calculations. Therefore, it is expected that LOGO-NNs with BP learning can be more effectively implemented as digital type circuits than the common MFNNs with the classical BP. Finally, it is shown by simulations that the proposed BP algorithm for LOGO-NNs has good performance in terms of the convergence rate, convergence speed and generalization capability.

- Publication
- IEICE TRANSACTIONS on Fundamentals Vol.E84-A No.3 pp.705-712

- Publication Date
- 2001/03/01

- Publicized

- Online ISSN

- DOI

- Type of Manuscript
- Special Section PAPER (Special Section of Selected Papers from the 13th Workshop on Circuits and Systems in Karuizawa)

- Category

The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.

Copy

Takeshi KAMIO, Hisato FUJISAKA, Mititada MORISUE, "Backpropagation Algorithm for LOGic Oriented Neural Networks with Quantized Weights and Multilevel Threshold Neurons" in IEICE TRANSACTIONS on Fundamentals,
vol. E84-A, no. 3, pp. 705-712, March 2001, doi: .

Abstract: Multilayer feedforward neural network (MFNN) trained by the backpropagation (BP) algorithm is one of the most significant models in artificial neural networks. MFNNs have been used in many areas of signal and image processing due to high applicability. Although they have been implemented as analog, mixed analog-digital and fully digital VLSI circuits, it is still difficult to realize their hardware implementation with the BP learning function efficiently. This paper describes a special BP algorithm for the logic oriented neural network (LOGO-NN) which we have proposed as a sort of MFNN with quantized weights and multilevel threshold neurons. Both weights and neuron outputs are quantized to integer values in LOGO-NNs. Furthermore, the proposed BP algorithm can reduce high precise calculations. Therefore, it is expected that LOGO-NNs with BP learning can be more effectively implemented as digital type circuits than the common MFNNs with the classical BP. Finally, it is shown by simulations that the proposed BP algorithm for LOGO-NNs has good performance in terms of the convergence rate, convergence speed and generalization capability.

URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e84-a_3_705/_p

Copy

@ARTICLE{e84-a_3_705,

author={Takeshi KAMIO, Hisato FUJISAKA, Mititada MORISUE, },

journal={IEICE TRANSACTIONS on Fundamentals},

title={Backpropagation Algorithm for LOGic Oriented Neural Networks with Quantized Weights and Multilevel Threshold Neurons},

year={2001},

volume={E84-A},

number={3},

pages={705-712},

abstract={Multilayer feedforward neural network (MFNN) trained by the backpropagation (BP) algorithm is one of the most significant models in artificial neural networks. MFNNs have been used in many areas of signal and image processing due to high applicability. Although they have been implemented as analog, mixed analog-digital and fully digital VLSI circuits, it is still difficult to realize their hardware implementation with the BP learning function efficiently. This paper describes a special BP algorithm for the logic oriented neural network (LOGO-NN) which we have proposed as a sort of MFNN with quantized weights and multilevel threshold neurons. Both weights and neuron outputs are quantized to integer values in LOGO-NNs. Furthermore, the proposed BP algorithm can reduce high precise calculations. Therefore, it is expected that LOGO-NNs with BP learning can be more effectively implemented as digital type circuits than the common MFNNs with the classical BP. Finally, it is shown by simulations that the proposed BP algorithm for LOGO-NNs has good performance in terms of the convergence rate, convergence speed and generalization capability.},

keywords={},

doi={},

ISSN={},

month={March},}

Copy

TY - JOUR

TI - Backpropagation Algorithm for LOGic Oriented Neural Networks with Quantized Weights and Multilevel Threshold Neurons

T2 - IEICE TRANSACTIONS on Fundamentals

SP - 705

EP - 712

AU - Takeshi KAMIO

AU - Hisato FUJISAKA

AU - Mititada MORISUE

PY - 2001

DO -

JO - IEICE TRANSACTIONS on Fundamentals

SN -

VL - E84-A

IS - 3

JA - IEICE TRANSACTIONS on Fundamentals

Y1 - March 2001

AB - Multilayer feedforward neural network (MFNN) trained by the backpropagation (BP) algorithm is one of the most significant models in artificial neural networks. MFNNs have been used in many areas of signal and image processing due to high applicability. Although they have been implemented as analog, mixed analog-digital and fully digital VLSI circuits, it is still difficult to realize their hardware implementation with the BP learning function efficiently. This paper describes a special BP algorithm for the logic oriented neural network (LOGO-NN) which we have proposed as a sort of MFNN with quantized weights and multilevel threshold neurons. Both weights and neuron outputs are quantized to integer values in LOGO-NNs. Furthermore, the proposed BP algorithm can reduce high precise calculations. Therefore, it is expected that LOGO-NNs with BP learning can be more effectively implemented as digital type circuits than the common MFNNs with the classical BP. Finally, it is shown by simulations that the proposed BP algorithm for LOGO-NNs has good performance in terms of the convergence rate, convergence speed and generalization capability.

ER -