A weight evolution algorithm for multi-layered network

Leung, S.H.; Luk, A.; Ng, Sin-Chun

doi:10.1109/icnn.1994.374298

Cited by 2 publications

(4 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ing BP falls off rapidly because gradient search techniques get trapped at local minima. When the nearly global minima's deeply hidden among the local minima, BP can end bouncing between local minima, especially for those nonlinearly separable pattern classification problems or complex function approximation problems (Leung, Luk, & Ng, 1994). The second drawback converges with the algorithm is sensitive to the early value, so it often converges to an inferior solution in a long training time.…”

Section: Learning Algorithms Of Artificial Neural Networkmentioning

confidence: 99%

G-HABC Algorithm for Training Artificial Neural Networks

Deris

Shah

Ghazali

et al. 2012

International Journal of Applied Metaheuristic Computing

View full text Add to dashboard Cite

Learning problems for Neural Network (NN) has widely been explored in the past two decades. Researchers have focused more on population-based algorithms because of its natural behavior processing. The population-based algorithms are Ant Colony Optimization (ACO), Artificial Bee Colony (ABC), and recently Hybrid Ant Bee Colony (HABC) algorithm produced an easy way for NN training. These social based techniques are mostly used for finding best weight values and over trapping local minima in NN learning. Typically, NN trained by traditional approach, namely the Backpropagation (BP) algorithm, has difficulties such as trapping in local minima and slow convergence. The new method named Global Hybrid Ant Bee Colony (G-HABC) algorithm which can overcome the gaps in BP is used to train the NN for Boolean Function classification task. The simulation results of the NN when trained with the proposed hybrid method were compared with that of Levenberg-Marquardt (LM) and ordinary ABC. From the results, the proposed G-HABC algorithm has shown to provide a better learning performance for NNs with reduced CPU time and higher success rates.

show abstract

Section: Learning Algorithms Of Artificial Neural Networkmentioning

confidence: 99%

G-HABC Algorithm for Training Artificial Neural Networks

Deris

Shah

Ghazali

et al. 2012

International Journal of Applied Metaheuristic Computing

View full text Add to dashboard Cite

show abstract

“…Therefore, the population is encouraged toward improved solution areas of the solution space. Populationbased optimization algorithms are categorized into two sections, namely, evolutionary algorithms (EA) and SI-based algorithms [17,23]. In EA, the major plan underlying this combination is to take the weight matrices of the ANN as individuals, to change the weights by some operations such as crossover and mutation, and to use the error produced by the ANN as the fitness measure that guides selection.…”

Section: Evolutionary Algorithms (Ea)mentioning

confidence: 99%

“…The different learning rules form the basis of various training techniques and their applicability is dependent on the NN architecture and the learning category being used. MLP has different learning algorithms for searching optimal weight values to minimize the error term between the output of the NNs and the actual desired output value like BP [14][15][16][17]. The error term is calculated by comparing the net output to the desired output and is then fed back through the network causing the synaptic weights to be changed in an effort to minimize error.…”

Section: Training Artificial Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

Untitled

2012

JCSCM

View full text Add to dashboard Cite

Neural network (NN) tools are suitable for many tasks such as classification, clustering, scheduling and prediction. NN performance depends on the strategy of learning a phenomenon, the number of hidden nodes, activation function and, of course, the behavior of the data. There are many techniques used for training NN, while the social insect's techniques become more focused by researchers because of its natural behavioral processing. The Artificial Bee Colony (ABC) algorithm has produced an easy way for solving combinatorial, statistical problems and for training NN by different organized agents. The objective of training NN is to adjust the weights so that application of a set of inputs produces the desired set of outputs. Normally, NN is trained by a standard backpropagation (BP) algorithm; however, BP is too slow for many applications and trapping in a local minima problem. To recover the above gap, the hybrid technique was used for training NN here. The hybrid of natural behavior agent ant and bee techniques was used for training NN. The simulation result of a Hybrid Ant Bee Colony (HABC) was compared with, ABC, BP Levenberg-Mardquart (LM) and BP Gradient Descent (GD) learning algorithms. According to experimental results, the proposed HABC algorithm did improve the classification accuracy for the Boolean function, and prediction of volcano time-series data, which was used to train the MLP.

show abstract

A weight evolution algorithm for multi-layered network

Cited by 2 publications

References 2 publications

G-HABC Algorithm for Training Artificial Neural Networks

G-HABC Algorithm for Training Artificial Neural Networks

Untitled

Contact Info

Product

Resources

About