Automated Test Input Generation for Convolutional Neural Networks by Implementing Multi-objective Evolutionary Algorithms

With the development of deep learning, the design of an appropriate network structure becomes fundamental. In recent years, the successful practice of Neural Architecture Search (NAS) has indicated that an automated design of the network structure can efficiently replace the design performed by human experts. Most NAS algorithms make the assumption that the overall structure of the network is linear and focus solely on accuracy to assess the performance of candidate networks. This paper introduces a novel NAS algorithm based on a multi-objective modeling of the network design problem to design accurate Convolutional Neural Networks (CNNs) with a small structure. The proposed algorithm makes use of a graph-based representation of the solutions which enables a high flexibility in the automatic design. Furthermore, the proposed algorithm includes novel ad-hoc crossover and mutation operators. We also propose a mechanism to accelerate the evaluation of the candidate solutions. Experimental results demonstrate that the proposed NAS approach can design accurate neural networks with limited size.

Download Full-text

Return, Diversification and Risk in Cryptocurrency Portfolios using Deep Recurrent Neural Networks and Multi-Objective Evolutionary Algorithms

2019 IEEE Congress on Evolutionary Computation (CEC) ◽

10.1109/cec.2019.8790121 ◽

2019 ◽

Author(s):

Ismael Estalayo ◽

Javier Del Ser ◽

Eneko Osaba ◽

Miren Nekane Bilbao ◽

Khan Muhammad ◽

...

Keyword(s):

Neural Networks ◽

Evolutionary Algorithms ◽

Recurrent Neural Networks ◽

Multi Objective

Download Full-text

Design space exploration of Convolutional Neural Networks based on Evolutionary Algorithms

Journal of Computational Vision and Imaging Systems ◽

10.15353/vsnl.v3i1.162 ◽

2017 ◽

Vol 3 (1) ◽

Cited By ~ 4

Author(s):

Abeer Al-Hyari ◽

Shawki Areibi

Keyword(s):

Neural Networks ◽

Genetic Algorithms ◽

Evolutionary Algorithms ◽

Convolutional Neural Networks ◽

Design Space Exploration ◽

Design Space ◽

Space Exploration ◽

Handwritten Digit ◽

Fully Connected ◽

The Given

This paper proposes a framework for design space exploration ofConvolutional Neural Networks (CNNs) using Genetic Algorithms(GAs). CNNs have many hyperparameters that need to be tunedcarefully in order to achieve favorable results when used for imageclassification tasks or similar vision applications. Genetic Algorithmsare adopted to efficiently traverse the huge search spaceof CNNs hyperparameters, and generate the best architecture thatfits the given task. Some of the hyperparameters that were testedinclude the number of convolutional and fully connected layers, thenumber of filters for each convolutional layer, and the number ofnodes in the fully connected layers. The proposed approach wastested using MNIST dataset for handwritten digit classification andresults obtained indicate that the proposed approach is able to generatea CNN architecture with validation accuracy up to 96.66% onaverage.

Download Full-text