Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/39028
Title: | Skipped Nonsynaptic Backpropagation for Interval-valued Long-term Cognitive Networks | Authors: | FRIAS DOMINGUEZ, Mabel Nápoles, Gonzalo Filiberto, Yaima Bello, Rafael VANHOOF, Koen |
Issue Date: | 2022 | Publisher: | INT ASSOC FOOD PROTECTION | Source: | Lagunas, Obdulia Pichardo; Martínez-Miranda, Juan; Martínez Seis, Bella (Ed.). INT ASSOC FOOD PROTECTION, p. 3 -14 | Series/Report: | Lecture Notes in Computer Science | Series/Report no.: | 13612 | Abstract: | The recently published Interval-valued Long-term Cognitive Networks have shown promising results when reasoning under uncertainty conditions. In these recurrent neural networks, the interval weights are learned using a nonsynaptic backpropagation learning algorithm. Similar to traditional propagation-based algorithms, this variant might suer from vanishing/exploding gradient issues. This paper proposes three skipped learning variants that do not use the backpropagation process to deliver the error signal to intermediate abstract layers (iterations in the recurrent neural network). The numerical simulations using 35 synthetic datasets conrm that the skipped variants work as well as the nonsynaptic backpropagation algorithm. | Keywords: | CRISPR-SeroSeq;Enrichment;Food safety;Poultry;Salmonella;Serovars | Document URI: | http://hdl.handle.net/1942/39028 | ISBN: | 978-3-031-19492-4 978-3-031-19493-1 |
DOI: | 10.1007/978-3-031-19493-1_1 | Category: | C1 | Type: | Proceedings Paper | Validations: | vabb 2024 |
Appears in Collections: | Research publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
paper 4.pdf Restricted Access | Peer-reviewed author version | 389.98 kB | Adobe PDF | View/Open Request a copy |
Pages from 978-3-031-19493-1.pdf Restricted Access | Published version | 224.59 kB | Adobe PDF | View/Open Request a copy |
Page view(s)
52
checked on Aug 6, 2023
Download(s)
6
checked on Aug 6, 2023
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.