Semisupervised Ordinal Regression Based on Empirical Risk Minimization

Ordinal regression is aimed at predicting an ordinal class label. In this letter, we consider its semisupervised formulation, in which we have unlabeled data along with ordinal-labeled data to train an ordinal regressor. There are several metrics to evaluate the performance of ordinal regression, such as the mean absolute error, mean zero-one error, and mean squared error. However, the existing studies do not take the evaluation metric into account, restrict model choice, and have no theoretical guarantee. To overcome these problems, we propose a novel generic framework for semisupervised ordinal regression based on the empirical risk minimization principle that is applicable to optimizing all of the metrics mentioned above. In addition, our framework has flexible choices of models, surrogate losses, and optimization algorithms without the common geometric assumption on unlabeled data such as the cluster assumption or manifold assumption. We provide an estimation error bound to show that our risk estimator is consistent. Finally, we conduct experiments to show the usefulness of our framework.

Principles governing the topological organization of object selectivities in ventral temporal cortex

To achieve the computational goal of rapidly recognizing miscellaneous objects in the environment despite large variations in their appearance, our mind represents objects in a high-dimensional object space to provide separable category information and enable the extraction of different kinds of information necessary for various levels of the visual processing. To implement this abstract and complex object space, the ventral temporal cortex (VTC) develops different object-selective regions with a certain topological organization as the physical substrate. However, the principle that governs the topological organization of object selectivities in the VTC remains unclear. Here, equipped with the wiring cost minimization principle constrained by the wiring length of neurons in the human temporal lobe, we constructed a hybrid self-organizing map (SOM) model as an artificial VTC (VTC-SOM) to explain how the abstract and complex object space is faithfully implemented in the brain. In two in silico experiments with the empirical brain imaging and single-unit data, our VTC-SOM predicted the topological structure of fine-scale functional regions (face-, object-, body-, and place-selective regions) and the boundary (i.e., middle Fusiform Sulcus) in large-scale abstract functional maps (animate vs. inanimate, real-word large-size vs. small-size, central vs. peripheral), with no significant loss in functionality (e.g., categorical selectivity, a hierarchy of view-invariant representations). These findings illustrated that the simple principle utilized in our model, rather than multiple hypotheses such as temporal associations, conceptual knowledge, and computational demands together, was apparently sufficient to determine the topological organization of object-selectivities in the VTC. In this way, the high-dimensional object space is implemented in a two-dimensional cortical surface of the brain faithfully.

Implementation of the personal data minimization principle in financial institutions: Lithuania’s case

Purpose The purpose of this paper is to assess such processing of personal data for identification purposes from the point of view of the principle of data minimisation, as set out in the EU’s General Data Protection Regulation (GDPR) and examine whether the processing of personal data for these purposes can be considered proportionate, i.e. whether it is performed for the purposes defined and only as much as is necessary. Design/methodology/approach In this paper, the authors discuss and present the relevant legal regulation and examine the goals and implementation of such regulation in Lithuania. This paper also examines the conditions for the lawful processing of personal data and their application for the above-mentioned purposes. Findings This paper addresses the problem that, on the one hand, financial institutions must comply with the objectives of collecting as much personal data as possible under the AML Directive (this practice is supported by the supervisory authority, the Bank of Lithuania), and, on the other hand, they must comply with the principle of data minimisation established by the GDPR. Originality/value Financial institutions process large amounts of personal data. These data are processed for different purposes. One of the purposes of processing personal data is (or may be) related to the prevention of money laundering and terrorist financing. In implementing the Know Your Customer principle and the relevant legal framework derived from the EU AML Directive, financial institutions collect various data, including projected account turnovers, account holders' relatives involved in politics, etc.

A numerical solution to thermo‐mechanical behavior of temperature dependent rotating functionally graded annulus disks

Purpose The purpose of this study is to investigate Thermo-mechanical limit elastic speed analysis of functionally graded (FG) rotating disks with the temperature-dependent material properties. Three different material models i.e. power law, sigmoid law and exponential law, along with varying disk profiles, namely, uniform thickness, tapered and exponential disk was considered. Design/methodology/approach The methodology adopted was variational principle wherein the solution was obtained by Galerkin’s error minimization principle. The Young’s modulus, coefficient of thermal expansion and yield stress variation were considered temperature-dependent. Findings The study shows a substantial increase in limit speed as disk profiles change from uniform thickness to exponentially varying thickness. At any radius in a disk, the difference in von Mises stress and yield strength shows the remaining stress-bearing capacity of material at that location. Practical implications Rotating disks are irreplaceable components in machinery and are used widely from power transmission assemblies (for example, gas turbine disks in an aircraft) to energy storage devices. During operations, these structures are mainly subjected to a combination of mechanical and thermal loadings. Originality/value The findings of the present study illustrate the best material models and their grading index, desired for the fabrication of uniform, as well as varying FG disks. Finite element analysis has been performed to validate the present study and good agreement between both the methods is seen.

υ-Nonparallel parametric margin fuzzy support vector machine

Classification problem is an important research direction in machine learning. υ-nonparallel support vector machine (υ-NPSVM) is an important classifier used to solve classification problems. It is widely used because of its structural risk minimization principle, kernel trick, and sparsity. However, when solving classification problems, υ-NPSVM will encounter the problem of sample noises and heteroscedastic noise structure, which will affect its performance. In this paper, two improvements are made on the υ-NPSVM model, and a υ-nonparallel parametric margin fuzzy support vector machine (par-υ-FNPSVM) is established. On the one hand, for the noises that may exist in the data set, the neighbor information is used to add fuzzy membership to the samples, so that the contribution of each sample to the classification is treated differently. On the other hand, in order to reduce the effect of heteroscedastic structure, an insensitive loss function is introduced. The advantages of the new model are verified through UCI machine learning standard data set experiments. Finally, Friedman test and Bonferroni-Dunn test are used to verify the statistical significance of it.

Combined plasma–coil optimization algorithms

Combined plasma–coil optimization approaches for designing stellarators are discussed and a new method for calculating free-boundary equilibria for multiregion relaxed magnetohydrodynmics (MRxMHD) is proposed. Four distinct categories of stellarator optimization, two of which are novel approaches, are the fixed-boundary optimization, the generalized fixed-boundary optimization, the quasi-free-boundary optimization, and the free-boundary (coil) optimization. These are described using the MRxMHD energy functional, the Biot–Savart integral, the coil-penalty functional and the virtual casing integral and their derivatives. The proposed free-boundary equilibrium calculation differs from existing methods in how the boundary-value problem is posed, and for the new approach it seems that there is not an associated energy minimization principle because a non-symmetric functional arises. We propose to solve the weak formulation of this problem using a spectral-Galerkin method, and this will reduce the free-boundary equilibrium calculation to something comparable to a fixed-boundary calculation. In our discussion of combined plasma–coil optimization algorithms, we emphasize the importance of the stability matrix.

Cooperation and Social Rules Emerging From the Principle of Surprise Minimization

The surprise minimization principle has been applied to explain various cognitive processes in humans. Originally describing perceptual and active inference, the framework has been applied to different types of decision making including long-term policies, utility maximization and exploration. This analysis extends the application of surprise minimization (also known as free energy principle) to a multi-agent setup and shows how it can explain the emergence of social rules and cooperation. We further show that in social decision-making and political policy design, surprise minimization is superior in many aspects to the classical approach of maximizing utility. Surprise minimization shows directly what value freedom of choice can have for social agents and why, depending on the context, they enter into cooperation, agree on social rules, or do nothing of the kind.

Directed acyclic graph fuzzy nonparallel support vector machine

Classification problem is an important research direction in machine learning. Nonparallel support vector machine (NPSVM) is an important classifier used to solve classification problems. It is widely used because of its structural risk minimization principle, kernel trick, and sparsity. When solving multi-class classification problems, NPSVM will encounter the problem of sample noises, low discrimination speed and unrecognized regions, which will affect its performance. In this paper, based on the multi-class NPSVM model, two improvements are made, and a directed acyclic graph fuzzy nonparallel support vector machine (DAG-F-NPSVM) model is established. On the one hand, for the noises that may exist in the data set, the density information is used to add fuzzy membership to the samples, so that the contribution of each samples to the classification is treated differently. On the other hand, in order to reduce the decision time and solve the problem of unrecognized regions, the theory of directed acyclic graph (DAG) is introduced. Finally, the advantages of the new model in classification accuracy and decision speed is verified through UCI machine learning standard data set experiments. Finally, Friedman test and Bonferroni-Dunn test are used to verify the statistical significance of this new method.