Particle Swarm Optimization for Automatically Evolving Convolutional Neural Networks for Image Classification

Abstract

Designing Convolutional Neural Networks from scratch is a time-consuming process that requires specialist expertise. While automated architecture generation algorithms have been proposed, the underlying search strategies generally are computationally expensive. The existing methods also do not explore the search space efficiently, and often lead to sub-optimal solutions. In this research, we propose a novel Particle Swarm Optimization (PSO)-based model for deep architecture generation to address the above challenges. Our proposed solution incorporates three new components. Firstly, a group-based encoding strategy is devised, which enforces the candidate networks to always follow the best practices. Specifically, it ensures that the number of groups can be adjusted in accordance with the input image size. By restricting the number of groups, we can adapt the frequency of the pooling operations toward the input image size. As such, it ascertains the position and maximum frequency of the pooling operations always result in a valid network architecture without the need for additional complex governing rules. Secondly, a new velocity updating mechanism is devised, which creates new network architectures by identifying the key network configuration differences. Thirdly, a new position updating mechanism using weighted velocity strengths is devised. Both the velocity and position updating mechanisms facilitate the proposed PSO-based model to search the intermediate positions of the particles' trajectories, allowing a better trade-off between diversification and intensification to be achieved. We employ eight well-known data sets, including Convex, Rectangles, MNIST and its variants, for model evaluation. The proposed PSO-based model achieves up to 7.58% improvement in accuracy and up to 63% reduction in computational cost, in comparison with those from the current state-of-the-art methods.

Deep Recurrent Neural Networks with Attention Mechanisms for Respiratory Anomaly Classification

“…Furthermore, the aforementioned A-BiLSTM architecture implemented in this research was shown to be highly effective, but with further experimentation with different layer and hyperparameter settings [24][25][26][27][28][29][30][31][32], additional improvements in performance could be made. Evolutionary algorithms [33][34][35][36][37][38][39][40][41][42][43][44][45][46][47][48][49] could also be exploited pertaining to the above parameter tuning as well as architecture generation processes. Moreover, it would also be beneficial to employ additional medical audio datasets to further evaluate model efficiency.…”

Using Convolution Neural Network for Defective Image Classification of Industrial Components

“…e convolutional neural network is also widely used in image classification. In order to solve the problem of large parameter space of training network, Lawrence [14] proposed a depth architecture generation model based on particle swarm optimization (PSO). It is used to search space effectively and generate an automatic evolution convolutional neural network to classify images.…”

Improved Search in Neuroevolution Using a Neural Architecture Classifier With the CNN Architecture Encoding as Feature Vector

“…Furthermore, Neuroevolution can find better CNN architectures for a specific task efficiently, allowing researchers without DL experience to find optimum CNN architectures for their fields of study [14], [43]. Neuroevolution has been applied to image classification [14], [31], [43], [44], [45], [46], [47], [48], [49], [50], [51], medical imaging segmentation [52], [53], and human activity recognition [54], among other problems [55], [56], [57], [58], [59], [60], [61].…”