Search
Search Results
-
Multivariate Scaling of the Characteristic Features Based on Pseudo-Inverse Operations for Recognition Problems Solving
AbstractSome approach to multidimensional information scaling of the characteristics features based on results of theory of perturbation of...
-
Generalized Inversion of Nonlinear Operators
Inversion of operators is a fundamental concept in data processing. Inversion of linear operators is well studied, supported by established theory....
-
Certified coordinate selection for high-dimensional Bayesian inversion with Laplace prior
We consider high-dimensional Bayesian inverse problems with arbitrary likelihood and product-form Laplace prior for which we provide a certified...
-
Theoretical Foundations for Pseudo-Inversion of Nonlinear Operators
The Moore-Penrose inverse is widely used in physics, statistics, and various fields of engineering. It captures well the notion of inversion of... -
Conjugate Gradient Method for finding Optimal Parameters in Linear Regression
Linear regression is one of the most celebrated approaches for modeling the relationship between independent and dependent variables in a prediction... -
Improving Self-supervised Dimensionality Reduction: Exploring Hyperparameters and Pseudo-Labeling Strategies
Dimensionality reduction (DR) is an essential tool for the visualization of high-dimensional data. The recently proposed Self-Supervised Network... -
Constructing a non-degenerate 2D chaotic map with application in irreversible PRNG
To solve the weakness of reversibility that exited in some pseudo-random number generators (PRNGs), we designed an enhanced chaos-based irreversible...
-
Forensic analysis and detection using polycolor model binary pattern for colorized images
Image recoloring is used to colorize historic grayscale images. Recoloring gives new life to grayscale images with realistic colors. Several...
-
Multimodal Inverse Cloze Task for Knowledge-Based Visual Question Answering
We present a new pre-training method, Multimodal Inverse Cloze Task, for Knowledge-based Visual Question Answering about named Entities (KVQAE).... -
An Evolutionary Multiobjective Optimization Algorithm Based on Manifold Learning
Multi-objective optimization problem is widespread in the real world. However, plenty of typical evolutionary multi-objective optimization (EMO)... -
Multi level of encryption and steganography depending on Rabinovich Hyperchaotic System & DNA
Securing confidential data is imperative in the modern digital era, where the escalating challenges in data security underscore the urgency to...
-
Adaptive output-feedback tracking for nonlinear systems with unknown control direction and generic inverse dynamics
This paper studies adaptive output-feedback tracking for a class of typical uncertain nonlinear systems. In the context of unknown control direction,...
-
Inverse Kinematics Solver Based on Evolutionary Algorithm and Gradient Descent for Free-Floating Space Robot
This paper investigates the inverse kinematics (IK) problem of free-floating space robot (FFSR) and proposes an IK solver called IK Solver Based on... -
Quick extreme learning machine for large-scale classification
The extreme learning machine (ELM) is a method to train single-layer feed-forward neural networks that became popular because it uses a fast...
-
Pattern recalling analysis of an auto-associative memory network using FFT and DWT
This study focused on recalling efficiency analysis of three different learning rules in Hopfield content addressable recurrent network for...
-
Zeroing Neural Network Based on Neutrosophic Logic for Calculating Minimal-Norm Least-Squares Solutions to Time-Varying Linear Systems
This paper presents a dynamic model based on neutrosophic numbers and a neutrosophic logic engine. The introduced neutrosophic logic/fuzzy adaptive...
-
A Novel Motion Planning Algorithm Based on RRT-Connect and Bidirectional Approach for Free-Floating Space Robot
This paper investigates the motion planning from initial configuration to goal configuration for Free-Floating Space Robot (FFSR) and suggests a... -
Hybrid Hopfield Neural Network
Hopfield and Tank have shown that a neural network can find solutions for complex optimization problems, although it can be trapped in a local...
-
A variational regularization method for solving the non-characteristic Cauchy problem in multiple dimensions
In this manuscript, we consider the non-characteristic Cauchy problem, which is naturally a general form including inverse heat conduction problem...
-
Learning to Drive by Watching YouTube Videos: Action-Conditioned Contrastive Policy Pretraining
Deep visuomotor policy learning, which aims to map raw visual observation to action, achieves promising results in control tasks such as robotic...