Search

One of the useful knowledge representation tools, which can describe the joint probability distribution between some random variables with a graphical model and can be trained by a dataset, is the Bayesian network (BN). A BN is composed of a network structure and a conditional probability distribution table for each node. Discovering an optimal BN structure is an NP‐hard optimization problem that various meta‐heuristic algorithms are applied to solve this problem by researchers. The genetic algorithms, ant colony optimization, evolutionary programming, artificial bee colony, and bacterial foraging optimization are some of the meta‐heuristic methods to solve this problem using a dataset. Most of these methods are applying a scoring metric to generate the best network structure from a set of candidates. A Fixed Structure Learning Automata‐Based (FSLA‐B) algorithm is presented in this paper to solve the structure learning problem of BNs. There is a fixed structure learning automaton for each pair of vertices in the BN's graph structure in the proposed algorithm. The action of this automaton determines the presence and direction of an edge between the vertices. The proposed algorithm performs a guided search procedure using the FSLA and escapes from local optimums. Several datasets are utilised in this paper to evaluate the performance of the proposed algorithm. By performing various experiments, multiple meta‐heuristic algorithms are compared with the introduced new one. The obtained results represented that the proposed algorithm could produce competitive results and find the near‐optimal solution for the BN structure learning problem. [ABSTRACT FROM AUTHOR]

The development of deep learning provides a new way for solving the colorization problem on the grayscale image. Excellent coding‐based methods appear in the automatic image colorization task, avoiding the unsaturated colour effect problem of previous methods based on the L2 loss function. Traditional neural networks come with high computational costs and a large number of parameters. Considering the limitation of memory and computing resources and aiming at lightweight, a novel grey image automatic colorization network is proposed. The basic idea of coding‐based methods is used, regarding the colorization task as a pixel‐level classification problem, meanwhile redesign and improve the colour encoding and decoding process. This network architecture leverages a lightweight convolution to reduce the computation and combines an efficient attention model to form a residual block as the kernel of the backbone network. Furthermore, an efficient image self‐attention mechanism placed at the end of the network is applied to enhance the ultimate colouring results. The method proposed in this paper can maintain the natural colouring effect and significantly reduce the computational amount and network model parameters. [ABSTRACT FROM AUTHOR]

Real‐time facial expression recognition is the basis for computers to understand human emotions and detect abnormalities in time. To effectively solve the problems of server overload and privacy information leakage, a real‐time facial expression recognition method based on iterative transfer learning and efficient attention network (EAN) for edge resource‐constrained scenes is proposed in this paper. Firstly, an EAN is designed with its parameter number and computation amount strictly limited by depth separable convolution and local channel attention mechanism. Then, the soft labels of facial expression data were obtained by EAN based on the idea of knowledge distillation, so as to provide more supervision information for the training process. Finally, an iterative transfer learning method of teacher‐student (T‐S) network was proposed; it refines the soft labels of the teacher network and further improves the recognition accuracy of the student network. The tests on the public datasets, FER2013 and RAF‐DB, show that this method can significantly reduce the model complexity and achieve high recognition accuracy. Compared with other advanced methods, the proposed method strikes a good balance between complexity and accuracy, and well meets the real‐time deployment requirements of facial expression recognition technology for edge resource‐constrained scenes. [ABSTRACT FROM AUTHOR]

In order to learn the mappings from words to referents, children must integrate co-occurrence information across individually ambiguous pairs of scenes and utterances, a challenge known as crosssituational word learning. In machine learning, recent multimodal neural networks have been shown to learn meaningful visual-linguistic mappings from cross-situational data, as needed to solve problems such as image captioning and visual question answering. These networks are potentially appealing as cognitive models because they can learn from raw visual and linguistic stimuli, something previous cognitive models have not addressed. In this paper, we examine whether recent machine learning approaches can help explain various behavioral phenomena from the psychological literature on crosssituational word learning. We consider two variants of a multimodal neural network architecture and look at seven different phenomena associated with cross-situational word learning and word learning more generally. Our results show that these networks can learn word-referent mappings from a single epoch of training, mimicking the amount of training commonly found in cross-situational word learning experiments. Additionally, these networks capture some, but not all of the phenomena we studied, with all of the failures related to reasoning via mutual exclusivity. These results provide insight into the kinds of phenomena that arise naturally from relatively generic neural network learning algorithms, and which word learning phenomena require additional inductive biases. [ABSTRACT FROM AUTHOR]

As the scale of federated learning expands, solving the Non‐IID data problem of federated learning has become a key challenge of interest. Most existing solutions generally aim to solve the overall performance improvement of all clients; however, the overall performance improvement often sacrifices the performance of certain clients, such as clients with less data. Ignoring fairness may greatly reduce the willingness of some clients to participate in federated learning. In order to solve the above problem, the authors propose Ada‐FFL, an adaptive fairness federated aggregation learning algorithm, which can dynamically adjust the fairness coefficient according to the update of the local models, ensuring the convergence performance of the global model and the fairness between federated learning clients. By integrating coarse‐grained and fine‐grained equity solutions, the authors evaluate the deviation of local models by considering both global equity and individual equity, then the weight ratio will be dynamically allocated for each client based on the evaluated deviation value, which can ensure that the update differences of local models are fully considered in each round of training. Finally, by combining a regularisation term to limit the local model update to be closer to the global model, the sensitivity of the model to input perturbations can be reduced, and the generalisation ability of the global model can be improved. Through numerous experiments on several federal data sets, the authors show that our method has more advantages in convergence effect and fairness than the existing baselines. [ABSTRACT FROM AUTHOR]

Recently, deep recurrent neural networks have achieved great success in various machine learning tasks, and have also been applied for sound event detection. The detection of temporally overlapping sound events in realistic environments is much more challenging than in monophonic detection problems. In this paper, we present an approach to improve the accuracy of polyphonic sound event detection in multichannel audio based on gated recurrent neural networks in combination with auditory spectral features. In the proposed method, human hearing perception-based spatial and spectral-domain noise-reduced harmonic features are extracted from multichannel audio and used as high-resolution spectral inputs to train gated recurrent neural networks. This provides a fast and stable convergence rate compared to long short-term memory recurrent neural networks. Our evaluation reveals that the proposed method outperforms the conventional approaches. [ABSTRACT FROM AUTHOR]

Over the years we have developed the Disciple theory, methodology, and family of tools for building knowledge-based agents. This approach consists of developing an agent shell that can be taught directly by a subject matter expert in a way that resembles how the expert would teach a human apprentice when solving problems in cooperation. This paper presents the most recent version of the Disciple approach and its implementation in the Disciple–RKF (rapid knowledge formation) system. Disciple–RKF is based on mixed-initiative problem solving, where the expert solves the more creative parts of the problem and the agent solves the more routine ones, integrated teaching and learning, where the agent helps the expert to teach it, by asking relevant questions, and the expert helps the agent to learn, by providing examples, hints, and explanations, and multistrategy learning, where the agent integrates multiple learning strategies, such as learning from examples, learning from explanations, and learning by analogy, to learn from the expert how to solve problems. Disciple–RKF has been applied to build learning and reasoning agents for military center of gravity analysis, which are used in several courses at the US Army War College. [ABSTRACT FROM AUTHOR]

Detecting shared bicycles is an essential and challenging task. Deep learning has been widely used in object detection tasks in urban scenes, such as vehicle detection. However, deep learning algorithms still face many difficulties and challenges in shared bicycle detection. For example, the problem of large deformation of shared bicycles and the problem of small targets because the camera is far away from the shared bicycles. In order to solve these problems, this study introduces the feature fusion module and deformable convolution into the object detection network, which improves the efficiency of shared bicycle detection. This study proposes an enhanced faster R‐CNN network (A classic two‐stage object detection network) for shared bicycle detection and a shared bicycle dataset (SBD) is constructed for model training and testing. Compared with the original faster R‐CNN, the mean average precision (mAP) of the enhanced method on SBD is improved by 13%, which indicates that the method provided in this study is more suitable for detecting shared bicycles. This study also conducts experiments on the Microsoft Common Objects (COCO) dataset, where this method achieves 40.2% of the mAP, which is 5.8% higher than faster R‐CNN before improvement. [ABSTRACT FROM AUTHOR]

Existing panoptic segmentation networks based on multiscale methods do not distinguish shared features according to different scales, which leads to a loss of feature information and suboptimal results. To solve this problem, the authors improve on UPSNet (a unified panoptic segmentation network) by introducing a multiscale fusion module cascaded between layers into the semantic segmentation head of UPSNet. On the one hand, this enriches the feature information for differently scaled features by cascading the feature information of adjacent scales, and on the other hand, the feature information at each scale can be combined adaptively to achieve a better segmentation effect. Furthermore, a frequency domain attention mechanism is introduced into the backbone network of UPSNet to improve the feature extraction ability of the backbone network by learning more frequency domain feature information. The experimental results of the authors' improved network on the Common Objects in Context (COCO) and Cityscapes data sets show that compared with UPSNet, the performance is significantly improved: the panoptic quality is improved by 0.9% and 1.6%, respectively. [ABSTRACT FROM AUTHOR]

High dimensionality of state representation is a major limitation for scale-up in reinforcement learning (RL). This work derives the knowledge of complexity reduction from partial solutions and provides algorithms for automated dimension reduction in RL. We propose the cascading decomposition algorithm based on the spectral analysis on a normalized graph Laplacian to decompose a problem into several subproblems and then conduct parameter relevance analysis on each subproblem to perform dynamic state abstraction. The elimination of irrelevant parameters projects the original state space into the one with lower dimension in which some subtasks are projected onto the same shared subtasks. The framework could identify irrelevant parameters based on performed action sequences and thus relieve the problem of high dimensionality in learning process. We evaluate the framework with experiments and show that the dimension reduction approach could indeed make some infeasible problem to become learnable. [ABSTRACT FROM AUTHOR]

Because of its convenience and strength in complex problem solving, case-based reasoning (CBR) has been widely used in various areas. One of these areas is customer classification, which classifies customers into either purchasing or non-purchasing groups. Nonetheless, compared to other machine learning techniques, CBR has been criticized because of its low prediction accuracy. Generally, in order to obtain successful results from CBR, effective retrieval of useful prior cases for the given problem is essential. However, designing a good matching and retrieval mechanism for CBR systems is still a controversial research issue. Most previous studies have tried to optimize the weights of the features or the selection process of appropriate instances. But these approaches have been performed independently until now. Simultaneous optimization of these components may lead to better performance than naive models. In particular, there have been few attempts to simultaneously optimize the weights of the features and the selection of instances for CBR. Here we suggest a simultaneous optimization model of these components using a genetic algorithm. To validate the usefulness of our approach, we apply it to two real-world cases for customer classification. Experimental results show that simultaneously optimized CBR may improve the classification accuracy and outperform various optimized models of CBR as well as other classification models including logistic regression, multiple discriminant analysis, artificial neural networks and support vector machines. [ABSTRACT FROM AUTHOR]