Explore the vast range of titles available.

Handwriting recognition refers to recognizing a handwritten input that includes character(s) or digit(s) based on an image. Because most applications of handwriting recognition in real life contain sequential text in various languages, there is a need to develop a dynamic handwriting recognition system. Inspired by the neuroevolutionary technique, this paper proposes a Dynamically Configurable Convolutional Recurrent Neural Network (DC-CRNN) for the handwriting recognition sequence modeling task. The proposed DC-CRNN is based on the Salp Swarm Optimization Algorithm (SSA), which generates the optimal structure and hyperparameters for Convolutional Recurrent Neural Networks (CRNNs). In addition, we investigate two types of encoding techniques used to translate the output of optimization to a CRNN recognizer. Finally, we proposed a novel hybridized SSA with Late Acceptance Hill-Climbing (LAHC) to improve the exploitation process. We conducted our experiments on two well-known datasets, IAM and IFN/ENIT, which include both the Arabic and English languages. The experimental results have shown that LAHC significantly improves the SSA search process. Therefore, the proposed DC-CRNN outperforms the handcrafted CRNN methods.

Machine Learning (ML) has revolutionized various fields, enabling the development of intelligent systems capable of solving complex problems. However, the process of manually designing and optimizing ML models is often time-consuming, labor-intensive, and requires specialized expertise. To address these challenges, Automatic Machine Learning (AutoML) has emerged as a promising approach that automates the process of selecting and optimizing ML models. Within the realm of AutoML, Neural Architecture Search (NAS) has emerged as a powerful technique that automates the design of neural network architectures, the core components of ML models. It has recently gained significant attraction due to its capability to discover novel and efficient architectures that surpass human-designed counterparts. This manuscript aims to present a systematic review of the literature on this topic published between 2017 and 2023 to identify, analyze, and classify the different types of algorithms developed for NAS. The methodology follows the guidelines of Systematic Literature Review (SLR) methods. Consequently, this study identified 160 articles that provide a comprehensive overview of the field of NAS, encompassing discussion on current works, their purposes, conclusions, and predictions of the direction of this science branch in its main core pillars: Search Space (SSp), Search Strategy (SSt), and Validation Strategy (VSt). Subsequently, the key milestones and advancements that have shaped the field are highlighted. Moreover, we discuss the challenges and open issues that remain in the field. We envision that NAS will continue to play a pivotal role in the advancement of ML, enabling the development of more intelligent and efficient ML models for a wide range of applications.

In recent years, deep learning (DL) has been widely studied using various methods across the globe, especially with respect to training methods and network structures, proving highly effective in a wide range of tasks and applications, including image, speech, and text recognition. One important aspect of this advancement is involved in the effort of designing and upgrading neural architectures, which has been consistently attempted thus far. However, designing such architectures requires the combined knowledge and know-how of experts from each relevant discipline and a series of trial-and-error steps. In this light, automated neural architecture search (NAS) methods are increasingly at the center of attention; this paper aimed at summarizing the basic concepts of NAS while providing an overview of recent studies on the applications of NAS. It is worth noting that most previous survey studies on NAS have been focused on perspectives of hardware or search strategies. To the best knowledge of the present authors, this study is the first to look at NAS from a computer vision perspective. In the present study, computer vision areas were categorized by task, and recent trends found in each study on NAS were analyzed in detail.

Wood veneer defect detection plays a vital role in the wood veneer production industry. Studies on wood veneer defect detection usually focused on detection accuracy for industrial applications but ignored algorithm execution speed; thus, their methods do not meet the required speed of online detection. In this paper, a new detection method is proposed that achieves high accuracy and a suitable speed for online production. Firstly, 2838 wood veneer images were collected using data collection equipment developed in the laboratory and labeled by experienced workers from a wood company. Then, an integrated model, glance multiple channel mask region convolution neural network (R-CNN), was constructed to detect wood veneer defects, which included a glance network and a multiple channel mask R-CNN. Neural network architect search technology was used to automatically construct the glance network with the lowest number of floating-point operations to pick out potential defect images out of numerous original wood veneer images. A genetic algorithm was used to merge the intermediate features extracted by the glance network. Multi-Channel Mask R-CNN was then used to classify and locate the defects. The experimental results show that the proposed method achieves a 98.70% overall classification accuracy and a 95.31% mean average precision, and only 2.5 s was needed to detect a batch of 50 standard images and 50 defective images. Compared with other wood veneer defect detection methods, the proposed method is more accurate and faster.

Due to the superiority of convolutional neural networks, many deep learning methods have been used in image classification. The enormous difference between natural images and remote sensing images makes it difficult to directly utilize or modify existing CNN models for remote sensing scene classification tasks. In this article, a new paradigm is proposed that can automatically design a suitable CNN architecture for scene classification. A more efficient search framework, RS-DARTS, is adopted to find the optimal network architecture. This framework has two phases. In the search phase, some new strategies are presented, making the calculation process smoother, and better distinguishing the optimal and other operations. In addition, we added noise to suppress skip connections in order to close the gap between trained and validation processing and ensure classification accuracy. Moreover, a small part of the neural network is sampled to reduce the redundancy in exploring the network space and speed up the search processing. In the evaluation phase, the optimal cell architecture is stacked to construct the final network. Extensive experiments demonstrated the validity of the search strategy and the impressive classification performance of RS-DARTS on four public benchmark datasets. The proposed method showed more effectiveness than the manually designed CNN model and other methods of neural architecture search. Especially, in terms of search cost, RS-DARTS consumed less time than other NAS methods.

Visually impaired people seek social integration, yet their mobility is restricted. They need a personal navigation system that can provide privacy and increase their confidence for better life quality. In this paper, based on deep learning and neural architecture search (NAS), we propose an intelligent navigation assistance system for visually impaired people. The deep learning model has achieved significant success through well-designed architecture. Subsequently, NAS has proved to be a promising technique for automatically searching for the optimal architecture and reducing human efforts for architecture design. However, this new technique requires extensive computation, limiting its wide use. Due to its high computation requirement, NAS has been less investigated for computer vision tasks, especially object detection. Therefore, we propose a fast NAS to search for an object detection framework by considering efficiency. The NAS will be used to explore the feature pyramid network and the prediction stage for an anchor-free object detection model. The proposed NAS is based on a tailored reinforcement learning technique. The searched model was evaluated on a combination of the Coco dataset and the Indoor Object Detection and Recognition (IODR) dataset. The resulting model outperformed the original model by 2.6% in average precision (AP) with acceptable computation complexity. The achieved results proved the efficiency of the proposed NAS for custom object detection.

Transformer networks present excellent performance in capturing long distance dependencies between different locations in the input sequence and are highly capable on a global scale. Recently, several neural architecture search (NAS) algorithms have been proposed for hyperspectral image (HSI) classification, which further improves the accuracy of HSI classification to a new level with more attention paid to local information. However, current two-channel network methods cannot focus on both local and global information of hyperspectral images, which leads to a decrease in the classification accuracy of this type of data. In this paper, a two-channel network named CTmixer-NAS is proposed for hyperspectral image classification. Combining the advantages of NAS and Transformer networks, local and global information is captured simultaneously. In the Transformer branch, the fusion of information at different self-coding layers is proposed. In the CNN branch, a high-performance network structure is automatically designed using NAS, which improves the accuracy of hyperspectral classification. The proposed approach saves labor cost, and the most suitable network structure can be searched according to different datasets, which makes the searched network structure present better generalization performance. CTmixer-NAS achieves the best performance in five hyperspectral datasets in comparative experiments.

Surrogate models are used by recently proposed algorithms as a means of forecasting neural architecture performance. Rather than training the network from scratch, which speeds up evaluation of performance in the search for neural architecture. However, collecting a sufficient number of labeled architectures for training surrogate models is a time-consuming process. We suggest a surrogate-assisted swarm optimization algorithm with network embedding for neural architecture search, as well as a generative adversarial networks for augmentation data (GNE-NAS) to improve the performance of surrogate models with limited training data. In this case, each architecture is meaningfully represented using an unsupervised learning technique. In the embedding space, architectures with a greater degree of structural similarity are positioned closer together. This proximity facilitates the training of surrogate models. Prior to training the surrogate model, we employ a generative adversarial network for data augmentation. This approach enhances the robustness of the surrogate model and concurrently reduces the need for a large number of real evaluations. The surrogate model achieves comparable or better performance when network embedding is applied, as demonstrated by experimental results on two distinct NASBench search spaces. Our proposed method, GNE-NAS, has been shown to outperform other state-of-the-art neural architecture search algorithms.

In view of the complexity and diversity of hyperspectral images (HSIs), the classification task has been a major challenge in the field of remote sensing image processing. Hyperspectral classification (HSIC) methods based on neural architecture search (NAS) is a current attractive frontier that not only automatically searches for neural network architectures best suited to the characteristics of HSI data, but also avoids the possible limitations of manual design of neural networks when dealing with new classification tasks. However, the existing NAS-based HSIC methods have the following limitations: (1) the search space lacks efficient convolution operators that can fully extract discriminative spatial–spectral features, and (2) NAS based on traditional differentiable architecture search (DARTS) has performance collapse caused by unfair competition. To overcome these limitations, we proposed a neural architecture search method with receptive field spatial–spectral attention (RFSS-NAS), which is specifically designed to automatically search the optimal architecture for HSIC. Considering the core needs of the model in extracting more discriminative spatial–spectral features, we designed a novel and efficient attention search space. The core component of this innovative space is the receptive field spatial–spectral attention convolution operator, which is capable of precisely focusing on the critical information in the image, thus greatly enhancing the quality of feature extraction. Meanwhile, for the purpose of solving the unfair competition issue in the traditional differentiable architecture search (DARTS) strategy, we skillfully introduce the Noisy-DARTS strategy. The strategy ensures the fairness and efficiency of the search process and effectively avoids the risk of performance crash. In addition, to further improve the robustness of the model and ability to recognize difficult-to-classify samples, we proposed a fusion loss function by combining the advantages of the label smoothing loss and the polynomial expansion perspective loss function, which not only smooths the label distribution and reduces the risk of overfitting, but also effectively handles those difficult-to-classify samples, thus improving the overall classification accuracy. Experiments on three public datasets fully validate the superior performance of RFSS-NAS.

Traditional neural architecture search (NAS) has a significant impact in computer vision by automatically designing network architectures for various tasks. In this paper, binarized neural architecture search (BNAS), with a search space of binarized convolutions, is introduced to produce extremely compressed models to reduce huge computational cost on embedded devices for edge computing. The BNAS calculation is more challenging than NAS due to the learning inefficiency caused by optimization requirements and the huge architecture space, and the performance loss when handling the wild data in various computing applications. To address these issues, we introduce operation space reduction and channel sampling into BNAS to significantly reduce the cost of searching. This is accomplished through a performance-based strategy that is robust to wild data, which is further used to abandon less potential operations. Furthermore, we introduce the upper confidence bound to solve 1-bit BNAS. Two optimization methods for binarized neural networks are used to validate the effectiveness of our BNAS. Extensive experiments demonstrate that the proposed BNAS achieves a comparable performance to NAS on both CIFAR and ImageNet databases. An accuracy of 96.53% vs. 97.22% is achieved on the CIFAR-10 dataset, but with a significantly compressed model, and a 40% faster search than the state-of-the-art PC-DARTS. On the wild face recognition task, our binarized models achieve a performance similar to their corresponding full-precision models.