Automated-tuned hyper-parameter deep neural network by using arithmetic optimization algorithm for Lorenz chaotic system

Abstract

<p>Deep neural networks (DNNs) are very dependent on their parameterization and require experts to determine which method to implement and modify the hyper-parameters value. This study proposes an automated-tuned hyper-parameter for DNN using a metaheuristic optimization algorithm, arithmetic optimization algorithm (AOA). AOA makes use of the distribution properties of mathematics’ primary arithmetic operators, including multiplication, division, addition, and subtraction. AOA is mathematically modeled and implemented to optimize processes across a broad range of search spaces. The performance of AOA is evaluated against 29 benchmark functions, and several real-world engineering design problems are to demonstrate AOA’s applicability. The hyper-parameter tuning framework consists of a set of Lorenz chaotic system datasets, hybrid DNN architecture, and AOA that works automatically. As a result, AOA produced the highest accuracy in the test dataset with a combination of optimized hyper-parameters for DNN architecture. The boxplot analysis also produced the ten AOA particles that are the most accurately chosen. Hence, AOA with ten particles had the smallest size of boxplot for all hyper-parameters, which concluded the best solution. In particular, the result for the proposed system is outperformed compared to the architecture tested with particle swarm optimization.</p>

Convolution neural network hyperparameter optimization using modified particle swarm optimization

“…The importance of selecting appropriate hyperparameters in CNN models has been demonstrated in previous research. However, manual hyperparameter selection methods have limitations due to their timeconsuming nature and lack of significant performance improvements [9]. Therefore, an automated approach to hyperparameter selection is necessary.…”

Big data clustering based on spark chaotic improved particle swarm optimization

“…Rather than advocating the combination of different algorithms, alternative methods leverage novel ideas derived from contemporary theories, such as chaos theory, to enhance their efficacy in a straightforward manner [38]− [40]. A promising approach to model systems heavily dependent on initial conditions, such as meta-heuristics, is through the use of chaotic maps.…”