A New Grammatical Evolution Method for Generating Deep Convolutional Neural Networks with Novel Topologies

Author(s)

Miranda, Thiago Zafalon ; Sardinha, Diorge Brognara ; Basgalupp, Marcio Porto ; Cerri, Ricardo ; ACM

• Document type: Journal article
• Source: PROCEEDINGS OF THE 2022 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE COMPANION, GECCO 2022; v. N/A, p. 4-pg., 2022-01-01.

Abstract

Neuroevolution, a sub-field of AutoML, utilizes evolutionary algorithms to automate the process of creating Deep Neural Networks architectures. For problems with complex objects, such as neural networks, Grammar-based Evolutionary Algorithms (GEs) can be used to simplify the implementation and the experimentation by using grammar rules to describe what the components of the complex object are and how they can be connected, that is, they elegantly describe the search space of the problem. In this work, we propose a GE algorithm based on Structured Grammatical Evolution to generate deep convolutional neural networks. Our work has two major contributions: first, the neural networks may contain an arbitrary number and arrangement of skip connections; second, our skip connections may upscale lower-resolution inputs, allowing the generation of architectures such as U-Net. Our best model achieved 0.85 accuracy on CIFAR-10. (AU)

• FAPESP's process: 22/03590-2 - GECCO 2022 - The Genetic and Evolutionary Computation Conference
• Grantee: Márcio Porto Basgalupp
• Support Opportunities: Research Grants - Meeting - Abroad
• FAPESP's process: 13/07375-0 - CeMEAI - Center for Mathematical Sciences Applied to Industry
• Grantee: Francisco Louzada Neto
• Support Opportunities: Research Grants - Research, Innovation and Dissemination Centers - RIDC
• FAPESP's process: 20/09835-1 - IARA - Artificial Intelligence in the Remaking of Urban Environments
• Grantee: André Carlos Ponce de Leon Ferreira de Carvalho
• Support Opportunities: Research Grants - Research Centers in Engineering Program