Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/30510
Title: | Synaptic Learning of Long-Term Cognitive Networks with Inputs | Authors: | Sosa, Richar Alfonso, Alejandro NAPOLES RUIZ, Gonzalo Bello, Rafael VANHOOF, Koen Nowé, Ann |
Issue Date: | 2019 | Publisher: | IEEE | Source: | Proceedings of the 2019 International Joint Conference on Neural Networks (IJCNN), IEEE, p. 1 -8 | Series/Report: | IEEE International Joint Conference on Neural Networks (IJCNN) | Abstract: | In contrast with the extense variety of machine learning algorithms, to fully automate the reasoning process, only a few can take advantage of the expert knowledge. Fuzzy Cognitive Maps (FCMs) are neural networks that can naturally integrate this kind of knowledge in the inference process. Nevertheless, FCMs have serious drawbacks difficult to overcome from the absence of an intrinsically learning algorithm or limited prediction horizon of the activation space of the neurons. Recently, some variants of the FCMs like Short-Term Cognitive Networks (STCN) and Long Term Cognitive Networks (LTCN) have been proposed to solve this problems. In this paper, we propose a new neural network model as a variant of LTCNs called Long-Term Cognitive Networks with Inputs (LTCNIs). A new kind of input neuron which is not present in the traditional FCMs approach or the derived algorithms STCNs and LTCNs is introduced, in order to model inputs like energy or mass in physical systems. The performance of the method, is discussed through the modeling of a passive circuit problem. As a second contribution, a new flexible reasoning strategy, which preserves the expert knowledge through the synaptic learning is presented. A synaptic learning based on a gradient descent method is implemented limited by a set of restrictions that preserves the model semantics. | Keywords: | Index Terms-Long-term memory;cognitive mapping;synaptic learning;modeling and simulation | Document URI: | http://hdl.handle.net/1942/30510 | Link to publication/dataset: | https://ieeexplore.ieee.org/xpl/conhome/8840768/proceeding | ISBN: | 9781728119854 | ISSN: | 2161-4407 | DOI: | 10.1109/IJCNN.2019.8852025 | ISI #: | WOS:000530893802086 | Rights: | Copyright 2020 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions. | Category: | C1 | Type: | Proceedings Paper | Validations: | ecoom 2022 vabb 2021 |
Appears in Collections: | Research publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
conference_041818_1.pdf Restricted Access | Published version | 435.81 kB | Adobe PDF | View/Open Request a copy |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.