Abstract

Generally, the decision rule for classifying unstructured data in an artificial neural network system depends on the sequence results of an activation function determined by vector–matrix multiplication between the input bias signal and the analog synaptic weight quantity of each node in a matrix array. Although a sequence-based decision rule can efficiently extract a common feature in a large data set in a short time, it can occasionally fail to classify similar species because it does not intrinsically consider other quantitative configurations of the activation function that affect the synaptic weight update. In this work, we implemented a simple run-off election-based decision rule via an additional filter evaluation to mitigate the confusion from proximity of output activation functions, enabling the improved training and inference performance of artificial neural network system. Using the filter evaluation selected via the difference among common features of classified images, the recognition accuracy achieved for three types of shoe image data sets reached ~ 82.03%, outperforming the maximum accuracy of ~ 79.23% obtained via the sequence-based decision rule in a fully connected single layer network. This training algorithm with an independent filter can precisely supply the output class in the decision step of the fully connected network.

Highlights

  • The decision rule for classifying unstructured data in an artificial neural network system depends on the sequence results of an activation function determined by vector–matrix multiplication between the input bias signal and the analog synaptic weight quantity of each node in a matrix array

  • The cumulative output signal is dependent on vector–matrix multiplication using the synaptic weights on each node, which can imitate integrated signal firing through the dendrite of the postneuron in the cortex neural n­ etwork[18,19,20,21,22,23,24,25]

  • When the difference in the activation function values between output neurons is relatively small and the sequence result is incorrectly ordered during training, the artificial neural network (ANN) system can guide the synaptic weights to the wrong updating direction in a given matrix according to the backpropagation learning r­ ule[30,31]

Read more

Summary

Introduction

The decision rule for classifying unstructured data in an artificial neural network system depends on the sequence results of an activation function determined by vector–matrix multiplication between the input bias signal and the analog synaptic weight quantity of each node in a matrix array. Using the filter evaluation selected via the difference among common features of classified images, the recognition accuracy achieved for three types of shoe image data sets reached ~ 82.03%, outperforming the maximum accuracy of ~ 79.23% obtained via the sequence-based decision rule in a fully connected single layer network. The resorting process with the 3-filter auxiliary networks can apply the change in the common feature of the classified output classes and modulation of synaptic weight for the fully connected single layer network (FCSN) which can be determining step in various neural network, leading to a more precise learning direction As a result, this method can achieve meaningful accuracy improvement for difficult shoe image recognition. This result suggests that filter evaluation based on the run-off election method in the determining step of the ANN system can improve the efficiency of the complex image classification process

Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call