Abstract
Wide datasets are usually used for training and validating neural networks, which can be later tuned in order to correct their final behaviors according to a few number of test cases proposed by users. In this paper we show how the FLOPER system developed in our research group is able to perform this last task after coding a neural network with a fuzzy logic language where program rules extend the classical notion of clause by including on their bodies both fuzzy connectives (useful for modeling activation functions of neurons) and truth degrees (associated with weights and biases in neural networks). We present an online tool which helps to select such operators and values in an automatic way, accomplishing with our recent technique for tuning this kind of fuzzy programs. Moreover, our experimental results reveal that our tool generates the choices that better fit user’s preferences in a very efficient way and producing relevant improvements on tuned neural networks.
This work has been partially supported by the EU (FEDER), the State Research Agency (AEI) and the Spanish Ministerio de Economía y Competitividad under grant TIN2016-76843-C4-2-R (AEI/FEDER, UE).
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.
This error is a non-negative real number (zero in the best case) obtained as the sum of the deviations of all registers in the dataset used at training time w.r.t. the execution of the trained network with the same cases.
References
Baldwin, J.F., Martin, T.P., Pilsworth, B.W.: Fril-Fuzzy and Evidential Reasoning in Artificial Intelligence. Wiley, Hoboken (1995)
Chollet, F., et al.: Keras: deep learning library for Theano and TensorFlow. 7(8), T1 (2015). https://keras.io/k
Ishizuka, M., Kanai, N.: Prolog-elf incorporating fuzzy logic. New Gener. Comput. 3(4), 479 (1985)
Julián-Iranzo, P., Moreno, G., Penabad, J.: Thresholded semantic framework for a fully integrated fuzzy logic language. J. Log. Algebraic Methods Program. 93, 42–67 (2017)
Lee, R.C.T.: Fuzzy logic and the resolution principle. In: Readings in Fuzzy Sets for Intelligent systems, pp. 442–452. Elsevier (1993)
Van Der Malsburg, C.: Frank Rosenblatt: principles of neurodynamics: perceptrons and the theory of brain mechanisms. In: Palm, G., Aertsen, A. (eds.) Brain Theory, pp. 245–248. Springer, Berlin Heidelberg (1986). https://doi.org/10.1007/978-3-642-70911-1_20
Medina, J., Ojeda-Aciego, M., Vojtáš, P.: Similarity-based Unification: a multi-adjoint approach. Fuzzy Sets Syst. 146, 43–62 (2004)
Moreno, G., Penabad, J., Riaza, J.A., Vidal, G.: Symbolic execution and thresholding for efficiently tuning fuzzy logic programs. In: Hermenegildo, M.V., Lopez-Garcia, P. (eds.) LOPSTR 2016. LNCS, vol. 10184, pp. 131–147. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-63139-4_8
Moreno, G., Riaza, J.A.: An online tool for tuning fuzzy logic programs. In: Costantini, S., Franconi, E., Van Woensel, W., Kontchakov, R., Sadri, F., Roman, D. (eds.) RuleML+RR 2017. LNCS, vol. 10364, pp. 184–198. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-61252-2_13
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Moreno, G., Pérez, J., Riaza, J.A. (2019). Fuzzy Logic Programming for Tuning Neural Networks. In: Fodor, P., Montali, M., Calvanese, D., Roman, D. (eds) Rules and Reasoning. RuleML+RR 2019. Lecture Notes in Computer Science(), vol 11784. Springer, Cham. https://doi.org/10.1007/978-3-030-31095-0_14
Download citation
DOI: https://doi.org/10.1007/978-3-030-31095-0_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-31094-3
Online ISBN: 978-3-030-31095-0
eBook Packages: Computer ScienceComputer Science (R0)