A new back-propagation algorithm with coupled neuron

Fukumi,; Omatu,

doi:10.1109/ijcnn.1989.118442

Cited by 5 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A novel stochastic technique for training the neural nets, which offers better performance on problems with large training sets, is recently proposed (Feng & Lu, 2019). In another paper (Fukumi & Omatu, 1991), an improvement in the convergence of the BP algorithm is reported by employing an alternative error performance function. The corresponding learning algorithm offers improved convergence performance compared to the conventional BP algorithm.…”

Section: Literature Surveymentioning

confidence: 99%

Fast and improved backpropagation learning of multi‐layer artificial neural network using adaptive activation function

Panda

2020

Expert Systems

View full text Add to dashboard Cite

In the conventional backpropagation (BP) learning algorithm used for the training of the connecting weights of the artificial neural network (ANN), a fixed slope−based sigmoidal activation function is used. This limitation leads to slower training of the network because only the weights of different layers are adjusted using the conventional BP algorithm. To accelerate the rate of convergence during the training phase of the ANN, in addition to updates of weights, the slope of the sigmoid function associated with artificial neuron can also be adjusted by using a newly developed learning rule. To achieve this objective, in this paper, new BP learning rules for slope adjustment of the activation function associated with the neurons have been derived. The combined rules both for connecting weights and slopes of sigmoid functions are then applied to the ANN structure to achieve faster training. In addition, two benchmark problems: classification and nonlinear system identification are solved using the trained ANN. The results of simulation-based experiments demonstrate that, in general, the proposed new BP learning rules for slope and weight adjustments of ANN provide superior convergence performance during the training phase as well as improved performance in terms of root mean square error and mean absolute deviation for classification and nonlinear system identification problems.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Fast and improved backpropagation learning of multi‐layer artificial neural network using adaptive activation function

Panda

2020

Expert Systems

View full text Add to dashboard Cite

show abstract

A new neuron model “cone” with fast convergence rate and its application to pattern recognition

Fukumi

Omatu

Teranishi

1991

Systems & Computers in Japan

View full text Add to dashboard Cite

show abstract

Rotation-invariant neural pattern recognition system with application to coin recognition

Fukumi

Omatu

Takeda

et al. 1992

IEEE Trans. Neural Netw.

138

View full text Add to dashboard Cite

In pattern recognition, it is often necessary to deal with problems to classify a transformed pattern. A neural pattern recognition system which is insensitive to rotation of input pattern by various degrees is proposed. The system consists of a fixed invariance network with many slabs and a trainable multilayered network. The system was used in a rotation-invariant coin recognition problem to distinguish between a 500 yen coin and a 500 won coin. The results show that the approach works well for variable rotation pattern recognition.

show abstract

A new back-propagation algorithm with coupled neuron

Cited by 5 publications

References 0 publications

Fast and improved backpropagation learning of multi‐layer artificial neural network using adaptive activation function

Fast and improved backpropagation learning of multi‐layer artificial neural network using adaptive activation function

A new neuron model “cone” with fast convergence rate and its application to pattern recognition

Rotation-invariant neural pattern recognition system with application to coin recognition

Contact Info

Product

Resources

About