Search

These instructions give guidelines for preparing papers for this publication. Presents information for authors publishing in this journal. [ABSTRACT FROM AUTHOR]

Though quite challenging, leveraging large-scale unlabeled or partially labeled data in learning systems (e.g., model/classifier training) has attracted increasing attentions due to its fundamental importance. To address this problem, many active learning (AL) methods have been proposed that employ up-to-date detectors to retrieve representative minority samples according to predefined confidence or uncertainty thresholds. However, these AL methods cause the detectors to ignore the remaining majority samples (i.e., those with low uncertainty or high prediction confidence). In this paper, by developing a principled active sample mining (ASM) framework, we demonstrate that cost-effective mining samples from these unlabeled majority data are a key to train more powerful object detectors while minimizing user effort. Specifically, our ASM framework involves a switchable sample selection mechanism for determining whether an unlabeled sample should be manually annotated via AL or automatically pseudolabeled via a novel self-learning process. The proposed process can be compatible with mini-batch-based training (i.e., using a batch of unlabeled or partially labeled data as a one-time input) for object detection. In this process, the detector, such as a deep neural network, is first applied to the unlabeled samples (i.e., object proposals) to estimate their labels and output the corresponding prediction confidences. Then, our ASM framework is used to select a number of samples and assign pseudolabels to them. These labels are specific to each learning batch based on the confidence levels and additional constraints introduced by the AL process and will be discarded afterward. Then, these temporarily labeled samples are employed for network fine-tuning. In addition, a few samples with low-confidence predictions are selected and annotated via AL. Notably, our method is suitable for object categories that are not seen in the unlabeled data during the learning process. Extensive experiments on two public benchmarks (i.e., the PASCAL VOC 2007/2012 data sets) clearly demonstrate that our ASM framework can achieve performance comparable to that of the alternative methods but with significantly fewer annotations. [ABSTRACT FROM AUTHOR]

Probabilistic classification vector machine (PCVM) is a sparse learning approach aiming to address the stability problems of relevance vector machine for classification problems. Because PCVM is based on the expectation maximization algorithm, it suffers from sensitivity to initialization, convergence to local minima, and the limitation of Bayesian estimation making only point estimates. Another disadvantage is that PCVM was not efficient for large data sets. To address these problems, this paper proposes an efficient PCVM (EPCVM) by sequentially adding or deleting basis functions according to the marginal likelihood maximization for efficient training. Because of the truncated prior used in EPCVM, two approximation techniques, i.e., Laplace approximation and expectation propagation (EP), have been used to implement EPCVM to obtain full Bayesian solutions. We have verified Laplace approximation and EP with a hybrid Monte Carlo approach. The generalization performance and computational effectiveness of EPCVM are extensively evaluated. Theoretical discussions using Rademacher complexity reveal the relationship between the sparsity and the generalization bound of EPCVM. [ABSTRACT FROM PUBLISHER]

Reservoir computing (RC) is a technique in machine learning inspired by neural systems. RC has been used successfully to solve complex problems such as signal classification and signal generation. These systems are mainly implemented in software, and thereby they are limited in speed and power efficiency. Several optical and optoelectronic implementations have been demonstrated, in which the system has signals with an amplitude and phase. It is proven that these enrich the dynamics of the system, which is beneficial for the performance. In this paper, we introduce a novel optical architecture based on nanophotonic crystal cavities. This allows us to integrate many neurons on one chip, which, compared with other photonic solutions, closest resembles a classical neural network. Furthermore, the components are passive, which simplifies the design and reduces the power consumption. To assess the performance of this network, we train a photonic network to generate periodic patterns, using an alternative online learning rule called first-order reduced and corrected error. For this, we first train a classical hyperbolic tangent reservoir, but then we vary some of the properties to incorporate typical aspects of a photonics reservoir, such as the use of continuous-time versus discrete-time signals and the use of complex-valued versus real-valued signals. Then, the nanophotonic reservoir is simulated and we explore the role of relevant parameters such as the topology, the phases between the resonators, the number of nodes that are biased and the delay between the resonators. It is important that these parameters are chosen such that no strong self-oscillations occur. Finally, our results show that for a signal generation task a complex-valued, continuous-time nanophotonic reservoir outperforms a classical (i.e., discrete-time, real-valued) leaky hyperbolic tangent reservoir (normalized~root\-mean\-square~errors=0.030~versus~NRMSE=0.127). [ABSTRACT FROM AUTHOR]

Transfer learning (TL) aims at solving the problem of learning an effective classification model for a target category, which has few training samples, by leveraging knowledge from source categories with far more training data. We propose a new discriminative TL (DTL) method, combining a series of hypotheses made by both the model learned with target training samples and the additional models learned with source category samples. Specifically, we use the sparse reconstruction residual as a basic discriminant and enhance its discriminative power by comparing two residuals from a positive and a negative dictionary. On this basis, we make use of similarities and dissimilarities by choosing both positively correlated and negatively correlated source categories to form additional dictionaries. A new Wilcoxon–Mann–Whitney statistic-based cost function is proposed to choose the additional dictionaries with unbalanced training data. Also, two parallel boosting processes are applied to both the positive and negative data distributions to further improve classifier performance. On two different image classification databases, the proposed DTL consistently outperforms other state-of-the-art TL methods while at the same time maintaining very efficient runtime. [ABSTRACT FROM AUTHOR]

Taking the assumption that data samples are able to be reconstructed with the dictionary formed by themselves, recent multiview subspace clustering (MSC) algorithms aim to find a consensus reconstruction matrix via exploring complementary information across multiple views. Most of them directly operate on the original data observations without preprocessing, while others operate on the corresponding kernel matrices. However, they both ignore that the collected features may be designed arbitrarily and hard guaranteed to be independent and nonoverlapping. As a result, original data observations and kernel matrices would contain a large number of redundant details. To address this issue, we propose an MSC algorithm that groups samples and removes data redundancy concurrently. In specific, eigendecomposition is employed to obtain the robust data representation of low redundancy for later clustering. By utilizing the two processes into a unified model, clustering results will guide eigendecomposition to generate more discriminative data representation, which, as feedback, helps obtain better clustering results. In addition, an alternate and convergent algorithm is designed to solve the optimization problem. Extensive experiments are conducted on eight benchmarks, and the proposed algorithm outperforms comparative ones in recent literature by a large margin, verifying its superiority. At the same time, its effectiveness, computational efficiency, and robustness to noise are validated experimentally. [ABSTRACT FROM AUTHOR]

In this article, a novel learning methodology is introduced for the problem of classification in the context of high-dimensional data. In particular, the challenges introduced by high-dimensional data sets are addressed by formulating a $L_{1}$ regularized zero-sum game where optimal sparsity is estimated through a two-player game between the penalty coefficients/sparsity parameters and the deep neural network weights. In order to solve this game, a distributed learning methodology is proposed where additional variables are utilized to derive layerwise cost functions. Finally, an alternating minimization approach developed to solve the problem where the Nash solution provides optimal sparsity and compensation through the classifier. The proposed learning approach is implemented in a parallel and distributed environment through a novel computational algorithm. The efficiency of the approach is demonstrated both theoretically and empirically with nine data sets. [ABSTRACT FROM AUTHOR]

Generating collision-free, time-efficient paths in an uncertain dynamic environment poses huge challenges for the formation control with collision avoidance (FCCA) problem in a leader–follower structure. In particular, the followers have to take both formation maintenance and collision avoidance into account simultaneously. Unfortunately, most of the existing works are simple combinations of methods dealing with the two problems separately. In this article, a new method based on deep reinforcement learning (RL) is proposed to solve the problem of FCCA. Especially, the learning-based policy is extended to the field of formation control, which involves a two-stage training framework: an imitation learning (IL) and later an RL. In the IL stage, a model-guided method consisting of a consensus theory-based formation controller and an optimal reciprocal collision avoidance strategy is designed to speed up training and increase efficiency. In the RL stage, a compound reward function is presented to guide the training. In addition, we design a formation-oriented network structure to perceive the environment. Long short-term memory is adopted to enable the network structure to perceive the information of obstacles of an uncertain number, and a transfer training approach is adopted to improve the generalization of the network in different scenarios. Numerous representative simulations are conducted, and our method is further deployed to an experimental platform based on a multiomnidirectional-wheeled car system. The effectiveness and practicability of our proposed method are validated through both the simulation and experiment results. [ABSTRACT FROM AUTHOR]

Ensuring the positive definiteness and avoiding ill conditioning of the Hessian update in the stochastic Broyden–Fletcher–Goldfarb–Shanno (BFGS) method are significant in solving nonconvex problems. This article proposes a novel stochastic version of a damped and regularized BFGS method for addressing the above problems. While the proposed regularized strategy helps to prevent the BFGS matrix from being close to singularity, the new damped parameter further ensures the positivity of the product of correction pairs. To alleviate the computational cost of the stochastic limited memory BFGS (LBFGS) updates and to improve its robustness, the curvature information is updated using the averaged iterate at spaced intervals. The effectiveness of the proposed method is evaluated through the logistic regression and Bayesian logistic regression problems in machine learning. Numerical experiments are conducted by using both synthetic data set and several real data sets. The results show that the proposed method generally outperforms the stochastic damped LBFGS (SdLBFGS) method. In particular, for problems with small sample sizes, our method has shown superior performance and is capable of mitigating ill-conditioned problems. Furthermore, our method is more robust to the variations of the batch size and memory size than the SdLBFGS method. [ABSTRACT FROM AUTHOR]

Distance metric learning is of fundamental interest in machine learning because the employed distance metric can significantly affect the performance of many learning methods. Quadratic Mahalanobis metric learning is a popular approach to the problem, but typically requires solving a semidefinite programming (SDP) problem, which is computationally expensive. The worst case complexity of solving an SDP problem involving a matrix variable of size D\times D with O (D) linear constraints is about O(D^6.5) using interior-point methods, where D is the dimension of the input data. Thus, the interior-point methods only practically solve problems exhibiting less than a few thousand variables. Because the number of variables is D (D+1)/2, this implies a limit upon the size of problem that can practically be solved around a few hundred dimensions. The complexity of the popular quadratic Mahalanobis metric learning approach thus limits the size of problem to which metric learning can be applied. Here, we propose a significantly more efficient and scalable approach to the metric learning problem based on the Lagrange dual formulation of the problem. The proposed formulation is much simpler to implement, and therefore allows much larger Mahalanobis metric learning problems to be solved. The time complexity of the proposed method is roughly O (D^3), which is significantly lower than that of the SDP approach. Experiments on a variety of data sets demonstrate that the proposed method achieves an accuracy comparable with the state of the art, but is applicable to significantly larger problems. We also show that the proposed method can be applied to solve more general Frobenius norm regularized SDP problems approximately. [ABSTRACT FROM PUBLISHER]

Catastrophic forgetting is a well-studied attribute of most parameterized supervised learning systems. A variation of this phenomenon, in the context of feedforward neural networks, arises when nonstationary inputs lead to loss of previously learned mappings. The majority of the schemes proposed in the literature for mitigating catastrophic forgetting were not data driven and did not scale well. We introduce the fixed expansion layer (FEL) feedforward neural network, which embeds a sparsely encoding hidden layer to help mitigate forgetting of prior learned representations. In addition, we investigate a novel framework for training ensembles of FEL networks, based on exploiting an information-theoretic measure of diversity between FEL learners, to further control undesired plasticity. The proposed methodology is demonstrated on a basic classification task, clearly emphasizing its advantages over existing techniques. The architecture proposed can be enhanced to address a range of computational intelligence tasks, such as regression problems and system control. [ABSTRACT FROM AUTHOR]

We propose a direct approach to learning sparse kernel classifiers for multi-instance (MI) classification to improve efficiency while maintaining predictive accuracy. The proposed method builds on a convex formulation for MI classification by considering the average score of individual instances for bag-level prediction. In contrast, existing formulations used the maximum score of individual instances in each bag, which leads to nonconvex optimization problems. Based on the convex MI framework, we formulate a sparse kernel learning algorithm by imposing additional constraints on the objective function to enforce the maximum number of expansions allowed in the prediction function. The formulated sparse learning problem for the MI classification is convex with respect to the classifier weights. Therefore, we can employ an effective optimization strategy to solve the optimization problem that involves the joint learning of both the classifier and the expansion vectors. In addition, the proposed formulation can explicitly control the complexity of the prediction model while still maintaining competitive predictive performance. Experimental results on benchmark data sets demonstrate that our proposed approach is effective in building very sparse kernel classifiers while achieving comparable performance to the state-of-the-art MI classifiers. [ABSTRACT FROM AUTHOR]