In a traditional machine learning task, the goal is training a classifier using only labeled data (data feature/label pairs) in order to be able to generalize on completely new data to be labeled by the classifier. Unluckily in many cases it is difficult, expensive or time consuming to obtain the labeled instances needed for training, also because we usually require a human supervisor to annota...

We consider active, semi-supervised learning in an offline transductive setting. We show that a previously proposed error bound for active learning on undirected weighted graphs can be generalized by replacing graph cut with an arbitrary symmetric submodular function. Arbitrary non-symmetric submodular functions can be used via symmetrization. Different choices of submodular functions give diff...

Semi-supervised active clustering (SSAC) utilizes the knowledge of a domain expert to cluster data points by interactively making pairwise “same-cluster” queries. However, it is impractical to ask human oracles to answer every pairwise query. In this paper, we study the influence of allowing “not-sure” answers from a weak oracle and propose algorithms to efficiently handle uncertainties. Differ...

In many applications the process of generating label information is expensive and time consuming. We present a new method that combines active and semi-supervised deep learning to achieve high generalization performance from a deep convolutional neural network with as few known labels as possible. In a setting where a small amount of labeled data as well as a large amount of unlabeled data is a...

In this paper, a semi-active control system for vibration mitigation of railway bridges is presented. The real time frequency response is estimated using a short-time Fourier transform, employing curve fitting to relevant peaks for increased accuracy. A control algorithm developed in MATLAB® is linked to a commercial FE-software, facilitating application on arbitrary structures. A numerical stu...

We consider a learning setting of importance to large scale machine learning: potentially unlimited data arrives sequentially, but only a small fraction of it is labeled. The learner cannot store the data; it should learn from both labeled and unlabeled data, and it may also request labels for some of the unlabeled items. This setting is frequently encountered in real-world applications and has...

This paper proposes a wavelet neurocontroller capable of self-adaptation and self-organization for uncertain systems controlled with semi-active devices, ideal candidates for control of large-scale civil structures. A condition on the sliding surface for cantilever-like structures is defined. The issue of applicability of the control solution to largescale civil structures is made the central t...

Data domain description techniques aim at deriving concise descriptions of objects belonging to a category of interest. For instance, the support vector domain description (SVDD) learns a hypersphere enclosing the bulk of provided unlabeled data such that points lying outside of the ball are considered anomalous. However, relevant information such as expert and background knowledge remain unuse...

This paper presents a novel semi-active Variable Stiffness and Damping Isolator (VSDI) for vibration mitigation of structures. The proposed VSDI system consists of a traditional steel-rubber vibration absorber, as the passive fail-safe element, and a magneto-rheological elastomer (MRE) with a controllable (or variable) stiffness and damping behavior, as the passive-active element. MRE is a type...

Most spam filters include some automatic pattern classifiers based on machine learning and pattern recognition techniques. Such classifiers often require a large training set of labeled emails to attain a good discriminant capability between spam and legitimate emails. In addition, they must be frequently updated because of the changes introduced by spammers to their emails to evade spam filter...