Generalized zero-shot learning (GZSL) aims to train a model for classifying data samples under the condition that some output classes are unknown during supervised learning. To address this challenging task, GZSL leverages semantic information of the seen (source) and unseen (target) classes to bridge the gap between both seen and unseen classes. Since its introduction, many GZSL models have been formulated. In this review paper, we present a comprehensive review on GZSL. Firstly, we provide an overview of GZSL including the problems and challenges. Then, we introduce a hierarchical categorization for the GZSL methods and discuss the representative methods in each category. In addition, we discuss the available benchmark data sets and applications of GZSL, along with a discussion on the research gaps and directions for future investigations.

With the recent advancement in digital technologies, the size of data sets has become too large in which traditional data processing and machine learning techniques are not able to cope with effectively [1, 2]. However, analyzing complex, high dimensional, and noise-contaminated data sets is a huge challenge, and it is crucial to develop novel algorithms that are able to summarize, classify, extract important information and convert them into an understandable form [3-5]. To undertake these problems, deep learning (DL) models have shown outstanding performances in the recent decade. Deep learning (DL) has revolutionized the future of artificial intelligence (AI). It has solved many complex problems that existed in the AI community for many years. In fact, DL models are deeper variants of artificial neural networks (ANNs) with multiple layers, whether linear or non-linear. Each layer is connected to its lower and upper layers through different weights. The capability of DL models in learning hierarchical features from various types of data, e.g., numerical, image, text and audio, makes them powerful in solving recognition, regression, semi-supervised and unsupervised problems [6-8]. In recent years, various deep architectures with different learning paradigm are quickly introduced to develop machines that can perform similar to human or even better in different domains of application such as medical diagnosis, self-driving cars, natural language and image processing, and predictive forecasting [9]. To show some recent advances of deep learning to some extent, we select 14 papers from the articles accepted in this journal to organize this issue. Focusing on recent developments in DL architectures and their applications, we classify the articles in this issue into four categories: (1) deep architectures and conventional neural networks, (2) incremental learning, (3) recurrent neural networks, and (4) generative models and adversarial examples. In the following, we give a brief summary of each category and then individually introduce related articles.

Fuzzy twin support vector machine (FTSVM) is an effective machine learning technique which is able to overcome the negative impact of noise and outliers in tackling data classification problems. In FTSVM, the degree of membership function in the sample space just described the space between input data and class center, whilst ignored the position of input data in the feature space and simply miscalculated the ledge support vectors as noises. This paper presents an intuitionistic fuzzy twin support vector machine (IFTSVM) which combines the idea of intuitionistic fuzzy number with twin SVM (TSVM). An adequate fuzzy membership is employed to reduce the noise brought by the pollutant inputs. Two functions, i.e., linear and nonlinear, are used to formulate two non-parallel hyperplanes. IFTSVM not only reduces the influence of noises, it also distinguishes the noises from the support vectors. Further, this modification can minimize a newly formulated structural risk and improve the classification accuracy. Two artificial and eleven benchmark problems are employed to evaluate the effectiveness of the proposed IFTSVM model. To quantify the results statistically, the bootstrap technique with the 95% confidence intervals is used. The outcome shows that IFTSVM is able to produce promising results as compared with those from the original SVM, Fuzzy SVM (FSVM), FTSVM and other models reported in the literature.

In this paper, a quadcopter UAV system based on neural network enhanced dynamic inversion control is proposed for multiple real-world application scenarios. A Sigma-Pi neural network (SPNN) is used as the compensator to reduce the model error and improve the system performance in the presence of uncertainties of UAV dynamics, payload and environment. Besides, we present a technical framework for fast and robust implementation of multi-purpose UAV systems, and develop a UAV control system evaluation testbed using a high-precision optical motion capture system. Both the simulation and experiment results demonstrate that the SPNN can reduce inversion errors related to UAV parameter uncertainties as well as tracking errors related to unknown disturbances and unmodeled dynamics. With the help of an online NN learning mechanism, the entire system can achieve much higher accuracy in attitude and trajectory control than conventional PID-based control systems under varying flight conditions.