Abstract
Unlike most computer vision approaches, which depend on hundreds or thousands of training images, humans can typically learn from a single visual example. Humans achieve this ability using background knowledge. Rule-based machine learning approaches such as Inductive Logic Programming (ILP) provide a framework for incorporating domain specific background knowledge. These approaches have the potential for human-like learning from small data or even one-shot learning, i.e. learning from a single positive example. By contrast, statistics based computer vision algorithms, including Deep Learning, have no general mechanisms for incorporating background knowledge. This paper presents an approach for one-shot rule learning called One-Shot Hypothesis Derivation (OSHD) based on using a logic program declarative bias. We apply this approach to two challenging human-like computer vision tasks: 1) Malayalam character recognition and 2) neurological diagnosis using retinal images. We compare our results with a state-of-the-art Deep Learning approach, called Siamese Network, developed for one-shot learning. The results suggest that our approach can generate human-understandable rules and outperforms the deep learning approach with a significantly higher average predictive accuracy.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Adé, H., Raedt, L.D., Bruynooghe, M.: Declarative bias for specific-to-general ILP systems. Mach. Learn. 20, 119–154 (1995)
Bennett, C.H., et al.: Contrasting advantages of learning with random weights and backpropagation in non-volatile memory neural networks. IEEE Access 7, 73938–73953 (2019)
Bouma, S.: One shot learning and Siamese networks in Keras (2017). https://sorenbouma.github.io/blog/oneshot/
Bromley, J., Guyon, I., LeCun, Y., Säckinger, E., Shah, R.: Signature verification using a "Siamese" time delay neural network. In: Proceedings of the 6th International Conference on Neural Information Processing Systems, pp. 737–744 (1993)
Cheung, C.Y.l., Ikram, M.K., Chen, C., Wong, T.Y.: Imaging retina to study dementia and stroke. Progr. Retinal Eye Res. 57, 89–107 (2017)
Varghese, D., Shankar, V.: A novel approach for single image super resolution using statistical mathematical model. IJAER 10(44) (2015)
Frost, S., Kanagasingam, Y., Sohrabi, H., Vignarajan, J., Bourgeat, P., et al.: Retinal vascular biomarkers for early detection and monitoring of Alzheimer’s disease. Transl. Psychiatry 3, e233 (2013)
Galdran, A., Meyer, M., Costa, P., MendonÇa, Campilho, A.: Uncertainty-aware artery/vein classification on retinal images. In: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), pp. 556–560 (2019)
Hart, W.E., Goldbaum, M., Côté, B., Kube, P., Nelson, M.R.: Measurement and classification of retinal vascular tortuosity. Int. J. Med. Inform. 53(2), 239–252 (1999)
Hinton, G.: Learning multiple layers of representation. Trends Cogn. Sci. 11, 428–434 (2007)
Hubbard, L.D., Brothers, R.J., King, W.N., et al.: Methods for evaluation of retinal microvascular abnormalities associated with hypertension/sclerosis in the atherosclerosis risk in communities study. Ophthalmology 106(12), 2269–2280 (1999)
Neethu, K.S., Varghese, D.: An incremental semi-supervised approach for visual domain adaptation. In: 2017 International Conference on Communication and Signal Processing (ICCSP), pp. 1343–1346 (2017)
Knudtson, M., Lee, K.E., Hubbard, L., Wong, T., et al.: Revised formulas for summarizing retinal vessel diameters. Curr. Eye Res. 27, 143–149 (2003)
Koch, G., Zemel, R., Salakhutdinov, R.: Siamese neural networks for one-shot image recognition. In: Proeedings of International Conference on Machine Learning, vol. 37 (2015)
Lake, B., Salakhutdinov, R., Gross, J., Tenenbaum, J.: One shot learning of simple visual concepts. In: Proceedings of the 33rd Annual Conference of the Cognitive Science Society, pp. 2568–2573 (2011)
Lake, B.M., Salakhutdinov, R., Tenenbaum, J.B.: Human-level concept learning through probabilistic program induction. Science 350(6266), 1332–1338 (2015)
Lalonde, M., Beaulieu, M., Gagnon, L.: Fast and robust optic disc detection using pyramidal decomposition and Hausdorff-based template matching. IEEE Trans. Med. Imaging 20, 1193–200 (2001)
Lamba, H.: One shot learning with Siamese networks using Keras (2019). https://towardsdatascience.com/one-shot-learning-with-siamese-networks-using-keras-17f34e75bb3d
Liu, X., He, P., Chen, W., Gao, J.: Multi-task deep neural networks for natural language understanding. CoRR 1901.11504 (2019)
Mainster, M.: The fractal properties of retinal vessels: embryological and clinical implications. Eye 4, 235–241 (1990)
McGrory, S., Taylor, A.M., Kirin, M., et al.: Retinal microvascular network geometry and cognitive abilities in community-dwelling older people: the Lothian birth cohort 1936 study. Ophthalmology 101(7), 993–998 (2017)
Muggleton, S.: Inverse entailment and Progol. N. Gener. Comput. 13, 245–286 (1995)
Muggleton, S.H., Santos, J.C.A., Tamaddoni-Nezhad, A.: TopLog: ILP using a logic program declarative bias. In: Garcia de la Banda, M., Pontelli, E. (eds.) ICLP 2008. LNCS, vol. 5366, pp. 687–692. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-89982-2_58
Muggleton, S., Lin, D., Tamaddoni-Nezhad, A.: Meta-interpretive learning of higher-order dyadic datalog: predicate invention revisited. Mach. Learn. 100(1), 49–73 (2015)
Muggleton, S., Dai, W.Z., Sammut, C., Tamaddoni-Nezhad, A.: Meta-interpretive learning from noisy images. Mach. Learn. 107 (2018)
Nedellec, C.: Declarative bias in ILP (1996)
Nguyen, A., Yosinski, J., Clune, J.: Deep neural networks are easily fooled: high confidence predictions for unrecognizable images. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 427–436 (2015)
Sudlow, C., et al.: UK biobank: an open access resource for identifying the causes of a wide range of complex diseases of middle and old age. PloS Med. (2015)
Tian, J., Smith, G., Guo, H., Liu, B., Pan, Z., et al.: Modular machine learning for Alzheimer’s disease classification from retinal vasculature. Sci. Rep. 11(1), 1–11 (2021)
Usman Akram, M., et al.: Geometric feature points based optical character recognition. In: 2013 IEEE Symposium on Industrial Electronics Applications, pp. 86–89 (2013)
Varghese, D., Tamaddoni-Nezhad, A.: One-shot rule learning for challenging character recognition. In: Proceedings of the 14th International Rule Challenge, CEUR, 2020, vol. 2644, pp. 10–27 (2020)
Zapata, M.A., Royo-Fibla, D., Font, O., Vela, J.I., et al.: Artificial intelligence to identify retinal fundus images, quality validation, laterality evaluation, macular degeneration, and suspected glaucoma. Clin. Ophthalmol. 14, 419 (2020)
Acknowledgements
Dany Varghese was supported by Vice Chancellor’s PhD Scholarship Award at the University of Surrey. Roman Bauer was supported by the Engineering and Physical Sciences Research Council of the United Kingdom (EP/S001433/1). The authors also thankfully acknowledge that the retinal images were obtained using UK Biobank application number 1969. Alireza Tamaddoni-Nezhad and Stephen Muggleton were supported by the EPSRC Network Plus grant on Human-Like Computing (HLC).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Varghese, D., Bauer, R., Baxter-Beard, D., Muggleton, S., Tamaddoni-Nezhad, A. (2022). Human-Like Rule Learning from Images Using One-Shot Hypothesis Derivation. In: Katzouris, N., Artikis, A. (eds) Inductive Logic Programming. ILP 2021. Lecture Notes in Computer Science(), vol 13191. Springer, Cham. https://doi.org/10.1007/978-3-030-97454-1_17
Download citation
DOI: https://doi.org/10.1007/978-3-030-97454-1_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-97453-4
Online ISBN: 978-3-030-97454-1
eBook Packages: Computer ScienceComputer Science (R0)