Abstract
In Artificial Neural Network (ANN) computing the learned knowledge about a problem domain is “implicitly” used by ANN-based system to carry on Machine Learning, Pattern Recognition and Reasoning in several application domains. In this work, by adopting a Weightless Neural Network (WNN) model of computation called DRASiW, we show how the knowledge of a problem, internally stored in a data representation called “Mental” Image (MI), can be made “explicit” both to perform additional and useful tasks in the same domain, and to better tune and adapt WNN behavior in order to improve its performance in the target domain. In this paper, three case studies of MI processing in the realm of WNN applications are discussed with the aim of proving the viability and the potentialities of exploiting internal knowledge of WNNs to self-adapt and improve their performance.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Just to mentions a fews: physical models, statistical methods with Gaussian mixtures, pixel clustering, image filtering (Kalman, Grabcut, etc.), particle filters and neuron network modeling.
- 2.
The proposed method participated in the international competition of CD methods on the video repository ChangeDetection.net in 2014, reporting the 3rd best score.
- 3.
References
Aleksander, I., De Gregorio, M., França, F.M.G., Lima, P.M.V., Morton, H.: A brief introduction to weightless neural systems. In: Proceedings of the 17st European Symposium on Artificial Neural Networks, pp. 299–305 (2009)
Aleksander, I., Morton, H.: An Introduction to Neural Computing. Chapman & Hall, London (1990)
Aleksander, I., Thomas, W.V., Bowden, P.A.: WISARD a radical step forward in image recognition. Sensor Rev. 4, 120–124 (1984)
Anguita, D., Ghio, A., Oneto, L., Parra, X., Reyes–Ortiz, J.L.: A public domain dataset for human activity recognition using smartphones. In: Proceedings of the 21st European Symposium on Artificial Neural Networks, pp. 437–442 (2013)
Bouwmans, T.: Recent advanced statistical background modeling for foreground detection: a systematic survey. Recent Patents Comput. Sci. 4(3), 147–176 (2011)
Burattini, E., De Gregorio, M., Tamburrini, G.: Generation and classification of recall images by neurosymbolic computation. In: Proceedings of the 2nd European Conference on Cognitive Modelling, pp. 127–134 (1998)
Davies, N., Siewiorek, D.P., Sukthankar, R.: Activity-based computing. IEEE Pervasive Comput. 7(2), 20–21 (2008)
De Gregorio, M.: On the reversibility of multi-discriminator systems. Technical Report 125/97, Istituto di Cibernetica, CNR (1997)
De Gregorio, M., Giordano, M.: Change Detection with Weightless Neural Networks, IEEE Change Detection Workshop – CVPR 2014, pp. 403–407 (2014)
Feng, T.J., Houkes, Z., Korsten, M., Spreeuwers, L.: Internal measuring models in trained neural networks for parameter estimation from images. In: IPA, pp. 230–233 (1992)
Grieco, B.P., Lima, P.M.V., De Gregorio, M., França, F.M.G.: Producing pattern examples from “mental” images. Neurocomputing 73(79), 1057–1064 (2010)
Ludermir, T.B., Carvalho, A.C., Braga, A.P., Souto, M.C.P.: Weightless neural models: a review of current and past works. Neural Comput. Surv. 2, 41–61 (1999)
Mantas, C., Puche, J., Mantas, J.: Extraction of similarity based fuzzy rules from artificial neural networks. Int. J. Approx. Reason. 43(2), 202–221 (2006)
Mc Ivor, A.: Background subtraction techniques. In: International Conference on Image and Vision Computing New Zealand, IVCNZ (2000)
Neagu, C.D., Palade, V.: Neural explicit and implicit knowledge representation. In: Proceedings of the 4th International Conference on Knowledge-Based Intelligent Engineering Systems and Allied Technologies, vol. 1, pp. 213–216 (2000)
Panahi, S., Sheikhi, S., Hadadan, S., Gheissari, N.: Evaluation of background subtraction methods. In: Digital Image Computing: Techniques and Applications, pp. 357–364 (2008)
Piccardi, M.: Background subtraction techniques: a review. In: IEEE International Conference on Systems, Man and Cybernetics, pp. 3099–3104 (2004)
Sato, M., Tsukimoto, H.: Rule extraction from neural networks via decision tree induction. In: International Joint Conference on Neural Networks, vol. 3, pp. 1870–1875 (2001)
Soares, C.M., da Silva, C.L.F., De Gregorio, M., França, F.M.G.: Uma implementação em software do classificador WiSARD. In: 5th SBRN, pp. 225–229 (1998)
Staffa, M., Rossi, S., Giordano, M., De Gregorio, M., Siciliano, B.: Segmentation performance in tracking deformable objects via WNNs. In: Robotics and Automation (ICRA) (2015)
Towell, G., Shavlik, J.: Extracting refined rules from knowledge-based neural networks. Mach. Learn. 13(1), pp. 71–101 (1993)
Yilmaz, A., Javed, O., Shah, M.: Object tracking: a survey. ACM Comput. Surv. 38(4), pp. 1–45 (2006)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this chapter
Cite this chapter
De Gregorio, M., Giordano, M. (2015). Exploiting “Mental” Images in Artificial Neural Network Computation. In: Zazzu, V., Ferraro, M., Guarracino, M. (eds) Mathematical Models in Biology. Springer, Cham. https://doi.org/10.1007/978-3-319-23497-7_3
Download citation
DOI: https://doi.org/10.1007/978-3-319-23497-7_3
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-23496-0
Online ISBN: 978-3-319-23497-7
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)