Abstract
Auto Resonance Network (ARN) is a biologically inspired generic non-linear data classifier with controllable noise tolerance useful in control applications like robotic path planning. It appears that multi-layer ARN can be useful in image recognition but such capabilities have not been studied. This paper presents a multi-layer ARN implementation for an image classification system for handwritten characters from MNIST data set. ARN nodes learn by tuning their coverage in response to statistical properties of the training data. This paper describes the effect of adjusting the resonance parameters like coverage and threshold on accuracy of recognition. ARN systems can be trained with a small training set. It has been possible to attain accuracy up to 93% with as few as 50 training samples. ARN nodes can spawn secondary nodes by perturbing the input and output similar to a mutated cell in a biological system. Use of input transformations to achieve required perturbation of the network is discussed in the paper. Results show that the network is able to learn quickly without any stability issues. The present work shows that reasonable level of image classification can be obtained using small sample training sets using resonance networks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Sabour, S., Frosst, N., Hinton, G.E.: Dynamic routing between capsules. In: 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA (2017)
Li, G., Hari, S.K.S., Sullivan, M., et al.: Understanding error propagation in deep learning neural network (DNN) accelerators and applications. In: ACM/IEEE Supercomputing Conference SC 2017, Denver, Co, USA, 17 November 2017
Aparanji, V.M., Wali, U., Aparna, R.: A novel neural network structure for motion control in joints. In: ICEECCOT-2016, IEEE Xplore Digital Library, pp. 227–232 (2016). Document no. 7955220
Mayannavar, S., Wali, U.: Hardware implementation of activation function for neural network processor. In: IEEE EECCMC, Vaniyambadi, India, 28–29, January 2018
Mayannavar, S., Wali, U.: Fast implementation of tunable ARN nodes. In: Abraham, A., Cherukuri, A.K., Melin, P., Gandhi, N. (eds.) ISDA 2018 2018. AISC, vol. 941, pp. 467–479. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-16660-1_46
Mayannavar, S., Wali, U.: Performance comparison of serial and parallel multipliers in massively parallel environment. In: 3rd ICEECCOT, Mysore, 14–15 December 2018. IEEE Xplore Digital Library, December 2018, in press
Aparanji, V.M., Wali, U.V., Aparna, R.: Pathnet: a neuronal model for robotic motion planning. In: Nagabhushan, T.N., Aradhya, V.N.M., Jagadeesh, P., Shukla, S., M. L., C. (eds.) CCIP 2017. CCIS, vol. 801, pp. 386–394. Springer, Singapore (2018). https://doi.org/10.1007/978-981-10-9059-2_34
Giuliodori, A., Lillo, R., Pena, D.: Handwritten digit classification. Working paper 11–17, Statistics and Economics Series 012, pp. 11–17, June 2011
Frangi, A.F., Niessen, W.J., Vincken, K.L., Viergever, M.A.: Multi-scale vessel enhancement filtering. In: International Conference on Medical Image Computing and Computer-Assisted Interventions – MICCAI 1998, pp. 130–137 (1998)
Patil, S., Wali, U., Swamy, M.K.: Application of vessel enhancement filtering for automated classification of human In-Vitro Fertilized images. In: 2016 International Conference on Electrical, Electronics, Communication, Computer and Optimization Techniques (ICEECCOT), Mysuru, India, 9–10 December 2016. IEEE Xplore (2017). https://doi.org/10.1109/iceeccot.2016.7955180
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems 25, pp. 1097–1105 (2012)
Babu, U.R., Venkateswarlu, Y., Chintha, A.K.: Handwritten digit recognition using K-nearest neighbour classifier. In: 2014 World Congress on Computing and Communication Technologies (WCCCT). IEEE (2014)
Patil, S., Wali, U., Swamy, M.K.: Deep learning techniques for automatic classification and analysis of human In-Vitro Fertilized (IVF) embryos. J. Emerg. Technol. Innov. Res. 5(2) (2018). ISSN 2349-5162
Juefei-Xu, F., Naresh Boddeti, V., Savvides, M.: Perturbative neural networks. arXiv digital library. Cornell University (2018)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Conference Paper at ICLR (2015). https://arxiv.org/pdf/1409.1556.pdf
LeCun, Y., Cortes, C., Burges, C.J.C.: The MNIST database of hand written digits. http://yann.lecun.com/exdb/mnist
Stephen, G.: Competitive learning- from interactive to action to adaptive resonance. Cogn. Sci. 11, 23–63 (1987)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Mayannavar, S., Wali, U. (2019). A Noise Tolerant Auto Resonance Network for Image Recognition. In: Gani, A., Das, P., Kharb, L., Chahal, D. (eds) Information, Communication and Computing Technology. ICICCT 2019. Communications in Computer and Information Science, vol 1025. Springer, Singapore. https://doi.org/10.1007/978-981-15-1384-8_13
Download citation
DOI: https://doi.org/10.1007/978-981-15-1384-8_13
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-1383-1
Online ISBN: 978-981-15-1384-8
eBook Packages: Computer ScienceComputer Science (R0)