Search

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]

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]

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]