What is he best known for?
The fields of study he is best known for:
- Statistics
- Artificial intelligence
- Mathematical optimization
His primary scientific interests are in Artificial neural network, Mathematical optimization, Recurrent neural network, Stochastic neural network and Exponential stability.
His research on Artificial neural network often connects related areas such as Quadratic programming.
In his work, Linear matrix inequality is strongly intertwined with Nonlinear programming, which is a subfield of Mathematical optimization.
His Recurrent neural network research is multidisciplinary, relying on both Robotics, Inverse kinematics and Control theory.
His study explores the link between Stochastic neural network and topics such as Lipschitz continuity that cross with problems in Lyapunov function.
His Exponential stability research incorporates elements of Variational inequality, Motion control, Projection and Robot manipulator.
His most cited work include:
- A projection neural network and its application to constrained optimization problems (239 citations)
- A general projection neural network for solving monotone variational inequalities and related optimization problems (220 citations)
- A general methodology for designing globally convergent optimization neural networks (207 citations)
What are the main themes of his work throughout his whole career to date?
His main research concerns Artificial neural network, Mathematical optimization, Recurrent neural network, Stochastic neural network and Algorithm.
His Artificial neural network research incorporates themes from Quadratic programming, Lyapunov function and Exponential stability.
His Mathematical optimization research includes elements of Nonlinear programming and Projection.
The study incorporates disciplines such as Time delay neural network, Probabilistic neural network, Optimization problem and Control theory in addition to Recurrent neural network.
His work in Stochastic neural network addresses subjects such as Cellular neural network, which are connected to disciplines such as Nonlinear system.
His Algorithm study combines topics in areas such as Discrete time and continuous time and Estimator.
He most often published in these fields:
- Artificial neural network (68.06%)
- Mathematical optimization (66.67%)
- Recurrent neural network (44.44%)
What were the highlights of his more recent work (between 2013-2020)?
- Mathematical optimization (66.67%)
- Algorithm (22.22%)
- Artificial neural network (68.06%)
In recent papers he was focusing on the following fields of study:
His primary areas of study are Mathematical optimization, Algorithm, Artificial neural network, Artificial intelligence and Recurrent neural network.
His work carried out in the field of Mathematical optimization brings together such families of science as Nonlinear programming and Nonlinear system.
He has included themes like Discrete time and continuous time and Robustness in his Algorithm study.
His work deals with themes such as Lyapunov function and Projection, which intersect with Artificial neural network.
In his study, which falls under the umbrella issue of Artificial intelligence, Kernel density estimation, Convolutional neural network and Deconvolution is strongly linked to Computer vision.
His Recurrent neural network study combines topics from a wide range of disciplines, such as Time delay neural network, Probabilistic neural network and Quadratic programming.
Between 2013 and 2020, his most popular works were:
- A Bi-Projection Neural Network for Solving Constrained Quadratic Optimization Problems (73 citations)
- A Complex-Valued Projection Neural Network for Constrained Optimization of Real Functions in Complex Variables (63 citations)
- A complex-valued neural dynamical optimization approach and its stability analysis (46 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Statistics
- Machine learning
Youshen Xia spends much of his time researching Mathematical optimization, Artificial neural network, Artificial intelligence, Recurrent neural network and Probabilistic neural network.
The concepts of his Mathematical optimization study are interwoven with issues in Dynamical systems theory, Projected dynamical system, Linear dynamical system, Random dynamical system and Nonlinear system.
His studies deal with areas such as Least squares and Pattern recognition as well as Artificial intelligence.
His study in Probabilistic neural network is interdisciplinary in nature, drawing from both Types of artificial neural networks, Lyapunov function, Projection, Stochastic neural network and Deep learning.
The concepts of his Stochastic neural network study are interwoven with issues in Quadratic programming and Feedforward neural network.
The study incorporates disciplines such as Speech recognition, Noise reduction and Autoregressive model in addition to Time delay neural network.
This overview was generated by a machine learning system which analysed the scientist’s
body of work. If you have any feedback, you can
contact us
here.
