Backpropagation Algorithm Adaptation Parameters Using Learning Automata

@article{Beigy2001BackpropagationAA,
  title={Backpropagation Algorithm Adaptation Parameters Using Learning Automata},
  author={H. Beigy and Mohammad Reza Meybodi},
  journal={International journal of neural systems},
  year={2001},
  volume={11 3},
  pages={
          219-28
        }
}
  • H. Beigy, M. Meybodi
  • Published 1 June 2001
  • Computer Science
  • International journal of neural systems
Despite of the many successful applications of backpropagation for training multi-layer neural networks, it has many drawbocks. For complex problems it may require a long time to train the networks, and it may not train at all. Long training time can be the result of the non-optimal parameters. It is not easy to choose appropriate value of the parameters for a particular problem. In this paper, by interconnection of fixed structure learning automata (FSLA) to the feedforward neural networks, we… 
View on PubMed
ceit.aut.ac.ir
26 Citations
Background Citations
3
Methods Citations
2

26 Citations

Citation Type

Citation Type

A learning automata-based algorithm for determination of the number of hidden units for three-layer neural networks
TLDR
This article presents an algorithm based on the proposed learning automaton, called survival algorithm, for determination of the number of hidden units of three layers neural networks, which has been tested on a number of problems and shown through simulations that networks generated are near optimal.
Modeling Ant Colony Algorithms Using Learning Automata
TLDR
This paper shows that ant colony algorithms can be modeled by a group of cooperating Learning Automata and then using a set of set of cooperating learning automata an algorithm for solving the routing problem in computer networks has been proposed.
Review on Methods to Fix Number of Hidden Neurons in Neural Networks
TLDR
The experimental results show that with minimum errors the proposed approach can be used for wind speed prediction in renewable energy systems and the perfect design of the neural network based on the selection criteria is substantiated using convergence theorem.
Utilizing Distributed Learning Automata to Solve Stochastic Shortest Path Problems
TLDR
It is shown that the shortest path is found with a probability as close as to unity by proper choice of the parameters of the proposed algorithms.
An iterative stochastic algorithm based on distributed learning automata for finding the stochastic shortest path in stochastic graphs
TLDR
This algorithm is based on distributed learning automata (DLA), and its objective is to use a DLA for finding the shortest path from the given source node to the given destination node whose weight is minimal in expected sense.
Learning automata based dynamic guard channel algorithms
Using learning automata in brain emotional learning for speech emotion recognition
TLDR
An improved version of brain emotional learning (BEL) model trained via learning automata (LA) for speech emotion recognition, which employs the theory of the stochastic LA in error back-propagation to train the BEL model in decreasing the high computational complexity of the traditional gradient method.
Author ' s personal copy Learning automata based dynamic guard channel algorithms q
TLDR
A new model for non stationary environments under which the proposed algorithms work and it is shown that a learning automaton operating under the proposed nonstationary environment equalizes its penalty strengths.
A learning automata-based adaptive uniform fractional guard channel algorithm
TLDR
The proposed algorithm uses a learning automaton to specify the acceptance/rejection of incoming new calls and it is shown that the given adaptive algorithm converges to an equilibrium point which is optimal for uniform fractional channel policy.
An Intelligent Ensemble Neural Network Model for Wind Speed Prediction in Renewable Energy Systems
TLDR
The computed results prove the effectiveness of the proposed ensemble neural network (ENN) model with respect to the considered error factors in comparison with that of the earlier models available in the literature.
...
1
2
3
...

References

SHOWING 1-10 OF 28 REFERENCES
Utilization of hierarchical structure stochastic automata for the back propagation method with momentum
  • N. Baba, H. Handa
  • Computer Science
    Proceedings of ICNN'95 - International Conference on Neural Networks
  • 1995
TLDR
It is suggested that hierarchical structure stochastic automata are quite helpful for finding an appropriate value of the momentum factor of the BP method with momentum.
Speed up learning and network optimization with extended back propagation
Efficient estimation of dynamically optimal learning rate and momentum for backpropagation learning
  • Xiao-Hu Yu, Guo-An Chen
  • Computer Science
    Proceedings of ICNN'95 - International Conference on Neural Networks
  • 1995
TLDR
A novel approach exploiting the derivatives w.r.t. the LR and MF is presented, which does not need to explicitly compute the first two order derivatives in weight space, but rather makes use of the information gathered from the forward and backward procedures.
Improved interpolation and extrapolation from continuous training examples using a new neuronal model with an adaptive steepness
  • D. Mclean, Z. Bandar, J. O'Shea
  • Computer Science
    Proceedings of ANZIIS '94 - Australian New Zealnd Intelligent Information Systems Conference
  • 1994
TLDR
A new fitting technique is introduced in which each neuron is given an adaptive steepness parameter, implemented as an extra internal connection, which is altered to better interpolate between the data points that its hyperplane divides.
Artificial neural network power system stabiliser trained with an improved BP algorithm
The paper presents an artificial neural network (ANN) power system stabiliser (NNPSS). The neural network in the proposed NNPSS is trained by an improved BP algorithm. The main difference between the…
Analysis of the misadjustment of BP network and an improved algorithm
  • Yang Jia, Yang Dali
  • Computer Science
    1993 IEEE International Symposium on Circuits and Systems
  • 1993
TLDR
Analysis and simulations show that the momentum misadjustment is a nonnegligible factor affecting the convergence precision of the BP network and an improved algorithm with stochastic attenuation momentum factor /splalpha/(k) can effectively cancel the negative effect of /spl alpha/ on a network and improve the convergence performance of the network.
A LMS algorithm with stochastic momentum factor
  • Yang Dali, Liu Ze-Min
  • Engineering
    [Proceedings] 1992 IEEE International Symposium on Circuits and Systems
  • 1992
A stochastic momentum factor least-mean-square algorithm (SMLMS) is proposed. The SMLMS algorithm considers the momentum factor alpha k as a stochastic attenuation factor so as to provide a better…
Learning Algorithms Theory and Applications
TLDR
Theory and Applications: Two-Person Zero-Sum Sequential, Stochastic Games with Imperfect and Incomplete Information - General Case, and The LAR?P - Algorithm and Statement of Results.
Learning automata - an introduction
TLDR
From the combination of knowledge and actions, someone can improve their skill and ability and this learning automata an introduction tells you that any book will give certain knowledge to take all benefits.
Learning internal representations by error propagation
...
1
2
3
...