A typical modern optimization technique is usually either heuristic or metaheuristic. This technique has managed to solve some optimization problems in the research area of science, engineering, and industry. However, implementation strategy of metaheuristic for accuracy improvement on convolution neural networks (CNN), a famous deep learning method, is still rarely investigated. Deep learning relates to a type of machine learning technique, where its aim is to move closer to the goal of artificial intelligence of creating a machine that could successfully perform any intellectual tasks that can be carried out by a human. In this paper, we propose the implementation strategy of three popular metaheuristic approaches, that is, simulated annealing, differential evolution, and harmony search, to optimize CNN. The performances of these metaheuristic methods in optimizing CNN on classifying MNIST and CIFAR dataset were evaluated and compared. Furthermore, the proposed methods are also compared with the original CNN. Although the proposed methods show an increase in the computation time, their accuracy has also been improved (up to 7.14 percent).
Convolutional neural network (CNN) is one of the most prominent architectures and algorithm in Deep Learning. It shows a remarkable improvement in the recognition and classification of objects. This method has also been proven to be very effective in a variety of computer vision and machine learning problems. As in other deep learning, however, training the CNN is interesting yet challenging. Recently, some metaheuristic algorithms have been used to optimize CNN using Genetic Algorithm, Particle Swarm Optimization, Simulated Annealing and Harmony Search. In this paper, another type of metaheuristic algorithms with different strategy has been proposed, i.e. Microcanonical Annealing to optimize Convolutional Neural Network. The performance of the proposed method is tested using the MNIST and CIFAR-10 datasets. Although experiment results of MNIST dataset indicate the increase in computation time (1.02x -1.38x), nevertheless this proposed method can considerably enhance the performance of the original CNN (up to 4.60%). On the CIFAR10 dataset, currently, state of the art is 96.53% using fractional pooling, while this proposed method achieves 99.14%.
Metaheuristic algorithm is a powerful optimization method, in which it can solve problems by exploring the ordinarily large solution search space of these instances, that are believed to be hard in general. However, the performances of these algorithms significantly depend on the setting of their parameter, while is not easy to set them accurately as well as completely relying on the problem's characteristic. To fine-tune the parameters automatically, many methods have been proposed to address this challenge, including fuzzy logic, chaos, random adjustment and others. All of these methods for many years have been developed indepen-dently for automatic setting of metaheuristic parameters, and integration of two or more of these methods has not yet much conducted. Thus, a method that provides advantage from combining chaos and random adjustment is proposed. Some popular metaheuristic algo-rithms are used to test the performance of the proposed method, i.e. simulated annealing, particle swarm optimization, differential evolution, and harmony search. As a case study of this research is contrast enhancement for images of Cameraman, Lena, Boat and Rice. In general, the simulation results show that the proposed methods are better than the original metaheuristic, chaotic metaheuristic, and metaheuristic by random adjustment. Keywords: metaheuristic, chaos, random adjustment, image contrast enhancement AbstrakAlgoritma Metaheuristic adalah metode pengoptimalan yang hebat, di mana ia dapat memecahkan masalah dengan menjelajahi ruang pencarian solusi yang biasanya besar dari contoh-contoh ini, yang diyakini sulit dilakukan secara umum. Namun, kinerja algoritme ini sangat bergantung pada pengaturan parameter mereka, namun tidak mudah untuk menetapkannya secara akurat serta sepenuhnya bergantung pada karakteristik masalah. Untuk menyempurnakan parameter secara otomatis, banyak metode telah diajukan untuk mengatasi tantangan ini, termasuk logika fuzzy, kekacauan, penyesuaian acak dan lain-lain. Semua metode ini selama bertahun-tahun telah dikembangkan secara terpisah untuk penentuan parameter metaheuristik secara otomatis, dan integrasi dua atau lebih dari metode ini belum banyak dilakukan. Dengan demikian, metode yang memberikan keuntungan dari penggabungan kekacauan dan penyesuaian acak pun diusulkan. Beberapa algoritma metaheuristik populer digunakan untuk menguji kinerja metode yang diusulkan, yaitu simulasi anil, optimasi partikel, evolusi diferensial, dan pencarian harmonis. Sebagai studi kasus penelitian ini adalah peningkatan kontras untuk citra Cameraman, Lena, Boat and Rice. Secara umum, hasil simulasi menunjukkan bahwa metode yang diusulkan lebih baik daripada metaheuristik asli, metaheuristik kacau, dan metaheuristik dengan penyesuaian acak.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.