Search Results

We introduce a new way of reasoning about invariance in terms of footprints in a program logic for object-oriented components. A footprint of an object-oriented component is formalized as a monadic predicate that describes which objects on the heap can be ...

Achieving the generalization of an invariant classifier from training domains to shifted test domains while simultaneously considering model fairness is a substantial and complex challenge in machine learning. Existing methods address the problem of ...

Current self-supervised representation learning methods are mainly based on contrastive learning and proxy tasks. These methods acquire semantically rich features by contrasting samples with invariant transformations (positive pairs) against other ...

Invariance properties are important for evolutionary algorithms to ensure consistent behavior and performance on broader classes of objective functions. Owing to the ranking-based transformation, several evolutionary algorithms for single-objective ...

While invariance of causal mechanisms has inspired recent work in both robust machine learning and causal inference, causal mechanisms may also vary over domains due to, for example, population-specific differences, the context of data collection, or ...

We consider the tracking problem under exogenous and parametric disturbances for nonlinear single-channel plants with mathematical model representable in a triangular input–output form. Within the framework of the block approach, we develop a ...

In practical applications of automatic control theory, one often deals with situations where the controls must range in some domain, in particular, take only nonnegative values. In this case, popular synthesis methods such as modal and optimal ...

We introduce subspace locally competitive algorithms (SLCAs), a family of novel network architectures for modeling latent representations of natural signals with group sparse structure. SLCA first layer neurons are derived from locally competitive ...

Images are often deformed for various reasons such as viewpoint movement, lens distortion, etc. It is desirable that image processing is invariant for such deformation. This paper proposes a new image smoothing which is invariant under general ...

Data augmentation is a widely used trick when training deep neural networks: in addition to the original data, properly transformed data are also added to the training set. However, to the best of our knowledge, a clear mathematical framework to explain ...

Treating neural network inputs and outputs as random variables, we characterize the structure of neural networks that can be used to model data that are invariant or equivariant under the action of a compact group. Much recent research has been devoted to ...

The wavelet scattering transform is an invariant and stable signal representation suitable for many signal processing and machine learning applications. We present the Kymatio software package, an easy-to-use, high-performance Python implementation of the ...

Given a response Y and a vector X = (X¹, ... ,X^d) of d predictors, we investigate the problem of inferring direct causes of Y among the vector X. Models for Y that use all of its causal covariates as predictors enjoy the property of being invariant across ...

Crowd employment is a new form of short-term and flexible employment that has emerged during the past decade. To understand this new form of employment, it is crucial to illuminate the underlying motivations of the workforce involved in it. This article ...

Class of affine nonlinear single-input single-output systems, where the relative degree of the equivalent form of the input-output is invariant to the presence of external, unmatched disturbances, is formalized. Methods of synthesis of a ...

A novel explicit constraint handling technique for the covariance matrix adaptation evolution strategy (CMA-ES) is proposed. The proposed constraint handling exhibits two invariance properties. One is the invariance to arbitrary element-wise increasing ...

Motivated by the result of invariance of regular-boundary open sets in [P. Cannarsa, G. D. Prato, and H. Frankowska, Indiana Univ. Math. J., 59 (2010), pp. 53--78] and multi-stability issues in gene networks, our paper focuses on three closely related ...

This article considers the issue of controlling a mobile robotic technological complex based on the use of predictive and invariant control methods for compensation of external indeterminate perturbations. Authors carry out the analysis of the ...

A method is developed for compensating the effect of wind disturbances on the flight path of an aircraft. Computer modeling of the method is performed. An approach is considered based on methods of the theory of absolute nonlinear invariance. The ...

For the orientation control system of the manipulator's end effector with electrical actuators, we develop a decomposition pr ocedure of feedback law design to track given trajectories in the end effector's coordinate system. Owing to the S-shaped ...