Search

When training samples are scarce, the semantic embedding technique, i. e., describing class labels with attributes, provides a condition to generate visual features for unseen objects by transferring the knowledge from seen objects. However, semantic descriptions are usually obtained in an external paradigm, such as manual annotation, resulting in weak consistency between descriptions and visual features. In this paper, we refine the coarse-grained semantic description for any-shot learning tasks, i. e., zero-shot learning (ZSL), generalized zero-shot learning (GZSL), and few-shot learning (FSL). A new model, namely, the semantic refinement Wasserstein generative adversarial network (SRWGAN) model, is designed with the proposed multihead representation and hierarchical alignment techniques. Unlike conventional methods, semantic refinement is performed with the aim of identifying a bias-eliminated condition for disjoint-class feature generation and is applicable in both inductive and transductive settings. We extensively evaluate model performance on six benchmark datasets and observe state-of-the-art results for any-shot learning; e. g., we obtain 70.2% harmonic accuracy for the Caltech UCSD Birds (CUB) dataset and 82.2% harmonic accuracy for the Oxford Flowers (FLO) dataset in the standard GZSL setting. Various visualizations are also provided to show the bias-eliminated generation of SRWGAN. Our code is available. [ABSTRACT FROM AUTHOR]

In industrial processes, soft sensor techniques are used to predict the hard-to-measure quality variables under the classic supervised learning paradigm. However, the data challenges, i. e., the widespread noises and inadequate labeled samples, usually make the data-driven sensors weak for application. In this paper, a simple but effective regularization method termed as adversarial smoothing regularization (ASR) is proposed, which measures the local smoothness of prediction around each input sample. By minimizing the divergence between the predictions for noisy and clean inputs, the proposed ASR regulates the learning model to be robust against local perturbation in a semi-supervised manner. Theoretical analysis explains the smoothing capability of ASR, and shows that it is helpful for the improvement of generalization performance. We also design a tri-regression framework to further use the information of unlabeled samples with pseudo labels and present the adversarial smoothing tri-regression (ASTR) model for soft sensor. Based on two industrial processes, comprehensive soft sensor experiments and noise tests are performed to show the robust semi-supervised learning capability of the proposed ASR and ASTR. • A new adversarial regularization is designed to measure the local smoothness around sample for robust modeling. • An adversarial tri-regression model is developed for soft sensor, which performs a semisupervised modeling. • The proposed technique could reduce the prediction variance and balance the prediction bias. • Experimental results on both simulated process and realistic process are provided. [ABSTRACT FROM AUTHOR]

• BNGBS is proposed to pursue an efficient learning process for classification task. • Triple incremental abilities are developed to learn more nodes, samples, and classes. • Extensive experiments are conducted on eight datasets to validate the effectiveness. As an ensemble algorithm, network boosting enjoys a powerful classification ability but suffers from the tedious and time-consuming training process. To tackle the problem, in this paper, a broad network gradient boosting system (BNGBS) is developed by integrating gradient boosting machine with broad networks, in which the classification loss caused by a base broad network is learned and eliminated by followed networks in a cascade manner. The proposed system is constructed as an additive model and can be easily optimized by a greedy strategy instead of the tedious back-propagation algorithm, resulting in a more efficient learning process. Meanwhile, triple incremental learning capabilities including the increment of feature nodes, increment of input samples, and increment of target classes are designed. The proposed system can be efficiently updated and expanded based on the current status instead of being entirely retrained when the demands for more feature nodes, input samples, and target classes are proposed. The node-increment ability allows to add more feature nodes into the built system if the current structures are not effective for learning. The sample-increment ability is developed to allow the model to keep learning from the coming batch data. The class-increment ability is used to tackle the issue that the coming batch data may contain unseen categories. In comparison with existing popular machine learning methods, comprehensive results based on eight benchmark datasets illustrate the effectiveness of the proposed broad network gradient boosting system for the classification task. [ABSTRACT FROM AUTHOR]

• A new ICA algorithm by concurrent consideration of independence and slowness is developed. • SICA is no longer restricted by the non-Gaussian hypothesis. • SICA explores the temporal information of slow varying to sort the features. • The supervised SICA is also deduced for the classification problem. For the process data analytics, numerous statistical methods are designed to extract informative features to reveal latent characteristics and correlation patterns among the variables. As a classic statistical method, independent component analysis extracts mutually independent components by searching for the maximum direction of non-Gaussianity from the mixed signals. However, the algorithm does not work for the latent Gaussian components, and the disorder of extracted features also brings trouble to the practical applications. In the present work, a slow independent component analysis algorithm is proposed to tackle the problems by concurrently considering the high-order statistic and slowness. It constructs a dual-objective optimization criterion function, simultaneously incorporating independence and slow varying characteristics into the feature extraction procedure, which ties together the ideas of independent component analysis and slow feature analysis under the same mathematical umbrella. Through adjusting the controllable sub-optimization objective weight, the proposed slow independent component analysis adds insight into the different roles of independence and slow varying characteristics in calibration modeling, and, thus, provides possibilities to combine the advantages of independent component analysis and slow feature analysis. Compared with the traditional method, the new algorithm no longer relies solely on higher-order statistic but also utilizes the slow varying characteristic to extract latent Gaussian or non-Gaussian components from mixed signals. Besides the unsupervised paradigm, the proposed algorithm is extended to the supervised form for classification task by utilizing the temporal structure as well as the label information. The effectiveness of the proposed algorithm is illustrated by blind source separation task and industrial fault diagnosis task using real-world datasets including speech signals and multiphase flow facility. [ABSTRACT FROM AUTHOR]