Structure and Base Analysis of Receptive Field Neural Networks in a Character Recognition Task
Open Access
Abstract
This paper explores extensions and restrictions of shallow convolutional neural networks with fixed kernels trained with a limited number of training samples. We extend the work recently done in research on Receptive Field Neural Networks (RFNN) and show their behaviour using different bases and step-by-step changes within the network architecture. To ensure the reproducibility of the results, we simplified the baseline RFNN architecture to a single-layer CNN network and introduced a deterministic methodology for RFNN training and evaluation. This methodology enabled us to evaluate the significance of changes using the (recently widely used in neural networks) Bayesian comparison. The results indicate that a change in the base may have less of an effect on the results than re-training using another seed. We show that the simplified network with tested bases has similar performance to the chosen baseline RFNN architecture. The data also show the positive impact of energy normalization of used filters, which improves the classification accuracy, even when using randomly initialized filters.Keywords
Funding Information
- Slovak Grant Agency VEGA (1/0202/23)
- Internal FEI STU Bratislava project (2022-23-04)
This publication has 40 references indexed in Scilit:
- Systematic evaluation of convolution neural network advances on the ImagenetComputer Vision and Image Understanding, 2017
- Using Gabor filter in 3D convolutional neural networks for human action recognition2017
- Gabor filter assisted energy efficient fast learning Convolutional Neural Networks2017
- ImageNet classification with deep convolutional neural networksCommunications of the ACM, 2017
- Statistical comparison of classifiers through Bayesian hierarchical modellingMachine Learning, 2017
- Gabor Feature Based Convolutional Neural Network for Object Recognition in Natural Scene2016
- Deep Residual Learning for Image Recognition2016
- A survey of transfer learningJournal of Big Data, 2016
- Rotation, Scaling and Deformation Invariant Scattering for Texture Discrimination2013
- Early Stopping — But When?2012