Abstract
One of the obvious differences between present machine learning and performance of human brain lies in the number labelled data that needs to be provided to the model for classification. The ultimate target of machine learning algorithms should be to learn from very few examples as demonstrated by human brain. The work presents an instance of reducing sample complexity in handwritten digit classification using the concept followed in object recognition with reduced training set by humans. The characteristics of selectivity and invariance to transformations in visual cortex lead to a feature representation which can learn from few examples. The same has been implemented for digit classification, and promising results are obtained which can be extended to variety of object classification/recognition tasks involving images, strings, documents, etc.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hubel, D.H., Wiesel, T.N.: Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex. J. Physiol. 160, 106–154 (1962)
Fukushima, K.: Neocognitron: a self organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybern. 36, 193–202 (1980)
LeCun, Y., Bengio, Y.: Convolutional networks for images, speech, and time-series. In: Arbib, M.A. (ed.), The Handbook of Brain Theory and Neural Networks. MIT Press (1995)
Riesenhuber, M., Poggio, T.: Hierarchical models of object recognition in cortex. Nat. Neurosci. 2, 1019–1025 (1999)
Serre, T., Wolf, L., Poggio, T.: Object recognition with features inspired by visual cortex. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. 2, pp. 994–1000 (2005)
Serre, T., Wolf, L., Bileschi, S., Riesenhuber, M., Poggio, T.: Robust object recognition with cortex-like mechanisms. IEEE Trans. Pattern Anal. Mach. Intell. 29, 411–426 (2007)
Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20, 273–297 (1995)
Ramakrishna Murty, M., Murthy, J.V.R., Prasad Reddy, P.V.G.D.: Text document classification based on a least square support vector machines with singular value decomposition. Int. J. Comput. Appl. (IJCA) 27, 21–26 (2011)
Navya Sri. Ramakrishna Murty, M.M., et al.: Robust features for emotion recognition from speech by using Gaussian mixture model classification. In: International Conference and Published Proceeding in SIST Series, vol. 2, pp. 437–444 Springer (2017)
Anselmi, F., Leibo, J.Z., Rosasco, L., Mutch, J., Tacchetti, A., Poggio, T.: Unsupervised learning of invariant representations with low sample complexity: the magic of sensory cortex or a new framework for machine learning. CBMM Memo No. 001, 1-24 (2014)
Smale, S., Rosasco, L., Bouvrie, J., Caponnetto, A., Poggio, T.: Mathematics of neural response. Found Comput. Math 10, 67–91 (2010)
Jaakel, F., Scholkopf, B., Wichmann, F.A.: A tutorial on kernel methods for categorization. J. Math. Psychol. 51, 343–358 (2007)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proceedings of CPVR (2005)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Thushar, A.K., Aradhya, V.N.M. (2020). Digit Classification Based on Mechanisms Used by Human Brain. In: Satapathy, S., Bhateja, V., Nguyen, B., Nguyen, N., Le, DN. (eds) Frontiers in Intelligent Computing: Theory and Applications. Advances in Intelligent Systems and Computing, vol 1014. Springer, Singapore. https://doi.org/10.1007/978-981-13-9920-6_29
Download citation
DOI: https://doi.org/10.1007/978-981-13-9920-6_29
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-9919-0
Online ISBN: 978-981-13-9920-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)