Hybridizing evolutionary computation and deep neural networks: an approach to handwriting recognition using committees and transfer learning

Baldominos Gómez, Alejandro; Sáez Achaerandio, Yago; Isasi, Pedro

Publication:
Hybridizing evolutionary computation and deep neural networks: an approach to handwriting recognition using committees and transfer learning

dc.affiliation.dpto	UC3M. Departamento de Informática	es
dc.affiliation.grupoinv	UC3M. Grupo de Investigación: Computación Evolutiva y Redes Neuronales (EVANNAI)	es
dc.contributor.author	Baldominos Gómez, Alejandro
dc.contributor.author	Sáez Achaerandio, Yago
dc.contributor.author	Isasi, Pedro
dc.contributor.funder	Ministerio de Educación, Cultura y Deporte (España)	es
dc.date.accessioned	2023-08-29T08:04:27Z
dc.date.available	2023-08-29T08:04:27Z
dc.date.issued	2019-03-26
dc.description.abstract	Neuroevolution is the field of study that uses evolutionary computation in order to optimize certain aspect of the design of neural networks, most often its topology and hyperparameters. The field was introduced in the late-1980s, but only in the latest years the field has become mature enough to enable the optimization of deep learning models, such as convolutional neural networks. In this paper, we rely on previous work to apply neuroevolution in order to optimize the topology of deep neural networks that can be used to solve the problem of handwritten character recognition. Moreover, we take advantage of the fact that evolutionary algorithms optimize a population of candidate solutions, by combining a set of the best evolved models resulting in a committee of convolutional neural networks. This process is enhanced by using specific mechanisms to preserve the diversity of the population. Additionally, in this paper, we address one of the disadvantages of neuroevolution: the process is very expensive in terms of computational time. To lessen this issue, we explore the performance of topology transfer learning: whether the best topology obtained using neuroevolution for a certain domain can be successfully applied to a different domain. By doing so, the expensive process of neuroevolution can be reused to tackle different problems, turning it into a more appealing approach for optimizing the design of neural networks topologies. After evaluating our proposal, results show that both the use of neuroevolved committees and the application of topology transfer learning are successful: committees of convolutional neural networks are able to improve classification results when compared to single models, and topologies learned for one problem can be reused for a different problem and data with a good performance. Additionally, both approaches can be combined by building committees of transferred topologies, and this combination attains results that combine the best of both	en
dc.description.sponsorship	This research is partially supported by the Spanish Ministry of Education, Culture and Sport under FPU fellowship with identifier FPU13/03917.	en
dc.identifier.bibliographicCitation	Baldominos, A., Saez, Y., & Isasi, P. (2019). Hybridizing Evolutionary Computation and Deep Neural Networks: An Approach to Handwriting Recognition Using Committees and Transfer Learning. Complexity, Vol. 2019, pp. 1-16.	es
dc.identifier.doi	https://doi.org/10.1155/2019/2952304
dc.identifier.issn	1076-2787
dc.identifier.publicationtitle	COMPLEXITY	es
dc.identifier.publicationvolume	2019	es
dc.identifier.uri	https://hdl.handle.net/10016/38123
dc.identifier.uxxi	AR/0000023656
dc.language.iso	eng	es
dc.publisher	Hindawi	es
dc.relation.projectID	Gobierno de España. FPU13/03917	es
dc.rights	© 2019 Alejandro Baldominos et al.	es
dc.rights	Atribución 3.0 España	*
dc.rights.accessRights	open access	es
dc.rights.uri	http://creativecommons.org/licenses/by/3.0/es/	*
dc.subject.eciencia	Informática	es
dc.subject.other	Neuroevolution	en
dc.subject.other	Neural networks	en
dc.title	Hybridizing evolutionary computation and deep neural networks: an approach to handwriting recognition using committees and transfer learning	en
dc.type	research article	*
dc.type.hasVersion	VoR	*
dspace.entity.type	Publication