Optimization of Convolutional Neural Network using Microcanonical Annealing Algorithm
This work addresses optimization difficulties in CNNs for computer vision tasks, but it is incremental as it applies a known metaheuristic algorithm to a new context.
The paper tackles the challenge of training convolutional neural networks (CNNs) by proposing the use of the Microcanonical Annealing algorithm for optimization, resulting in performance improvements such as up to 4.60% enhancement on MNIST and achieving 99.14% accuracy on CIFAR-10, surpassing the state-of-the-art of 96.53%.
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\%.