Please use this identifier to cite or link to this item:
Title: Design and independent training of composable and reusable neural modules
Authors: Castillo Bolado, David Alejandro 
Guerra-Artal, Cayetano 
HernÁndez-Tejera, Mario 
UNESCO Clasification: 120304 Inteligencia artificial
Keywords: Compositionality
Learning by role
Modular training
Modularity, et al
Issue Date: 2021
Journal: Neural Networks 
Abstract: Monolithic neural networks and end-to-end training have become the dominating trend in the field of deep learning, but the steady increase in complexity and training costs has raised concerns about the effectiveness and efficiency of this approach. We propose modular training as an alternative strategy for building modular neural networks by composing neural modules that can be trained independently and then kept for future use. We analyse the requirements and challenges regarding modularity and compositionality and, with that information in hand, we provide a detailed design and implementation guideline. We show experimental results of applying this modular approach to a Visual Question Answering (VQA) task parting from a previously published modular network and we evaluate its impact on the final performance, with respect to a baseline trained end-to-end. We also perform compositionality tests on CLEVR.
ISSN: 0893-6080
DOI: 10.1016/j.neunet.2021.03.034
Source: Neural Networks [ISSN 0893-6080], v. 139, p. 294-304, (Julio 2021)
Appears in Collections:Artículos
Adobe PDF (853,53 kB)
Show full item record

Page view(s)

checked on Mar 23, 2024


checked on Mar 23, 2024

Google ScholarTM




Export metadata

Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.