Abstract
Convolutional neural networks have a broad spectrum of practical applications in computer vision. Currently, much of the data come from images, and it is crucial to have an efficient technique for processing these large amounts of data. Convolutional neural networks have proven to be very successful in tackling image processing tasks. However, the design of a network structure for a given problem entails a fine-tuning of the hyperparameters in order to achieve better accuracy. This process takes much time and requires effort and expertise from the domain. Designing convolutional neural networks’ architecture represents a typical NP-hard optimization problem, and some frameworks for generating network structures for a specific image classification tasks have been proposed. To address this issue, in this paper, we propose the hybridized monarch butterfly optimization algorithm. Based on the observed deficiencies of the original monarch butterfly optimization approach, we performed hybridization with two other state-of-the-art swarm intelligence algorithms. The proposed hybrid algorithm was firstly tested on a set of standard unconstrained benchmark instances, and later on, it was adapted for a convolutional neural network design problem. Comparative analysis with other state-of-the-art methods and algorithms, as well as with the original monarch butterfly optimization implementation was performed for both groups of simulations. Experimental results proved that our proposed method managed to obtain higher classification accuracy than other approaches, the results of which were published in the modern computer science literature.
Highlights
Convolutional neural networks (CNNs) [1] are a special type of deep learning models that have demonstrated high performance on different types of digital image processing tasks
In 1959, Hubel and Wiesel [9] published one of the most influential papers in this area. They conducted many different experiments with the aim to understand how neurons work in the visual cortex. They found that the primary visual cortex in the brain has a hierarchical organization with simple and complex neurons and the visual processing always starts with simple structures such as oriented edges, and the complex cells receive input from the lower-level simple cells
First we present the result of the proposed monarch butterfly optimization (MBO)-ABCFE algorithm on unconstrained benchmark function experiments and the comparison with other metaheuristics
Summary
Convolutional neural networks (CNNs) [1] are a special type of deep learning models that have demonstrated high performance on different types of digital image processing tasks. CNNs have become a fast-growing field in recent years, though their evolution started much earlier. In 1959, Hubel and Wiesel [9] published one of the most influential papers in this area. They conducted many different experiments with the aim to understand how neurons work in the visual cortex. They found that the primary visual cortex in the brain has a hierarchical organization with simple and complex neurons and the visual processing always starts with simple structures such as oriented edges, and the complex cells receive input from the lower-level simple cells
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have