Add to ORKGAbstract: This paper presents a method for stabilizing and robustifying the artificial neural networks trained by utilizing the gradient descent. The method proposed constructs a dynamic model of the conventional update mechanism and derives the stabilizing values of the learning rate. The stability in this context corresponds to the convergence in adjustable parameters of the neural network structure. It is shown that the selection of the learning rate as imposed by the proposed algorithm results in stable training in the sense of Lyapunov. Furthermore, the algorithm devised filters out the high frequency dynamics of the gradient descent method. The method analyzed in this paper integrates the gradient descent technique with variable struc...
[[abstract]]This paper presents a stability method which is based on the stability condition of slid...
The paper is concerned with the application of quadratic optimization for motion control to feedback...
In this work possibility of improvement of algorithms of neural control of anthropomorphic manipulat...
This paper discusses the stabilizability of arti®cial neural networks trained by utilizing the gradi...
Abstract—In this paper, a stabilization method based on the input–output conicity criterion is prese...
In this work, a novel and model-based artificial neural network (ANN) training method is developed s...
We aim at the optimization of the tracking control of a robot to improve the robustness, under the e...
67 p.Neural networks are widely used in industry fields, like robotic and process controllers. Exten...
The stability of learning rate in neural network identifiers and controllers is one of the challengi...
A robust neural network is proposed for use with a proportional fixed control scheme for robot contr...
Recurrent Neural Network (RNN) is a powerful tool for both theoretical modelling and practical appli...
Improving adversarial robustness of neural networks remains a major challenge. Fundamentally, traini...
grantor: University of TorontoAn artificial neural network (ANN) control method is develop...
To solve the problem of convergence to a local optimum in the multi-layer feedforward neural network...
Abstract—This paper presents a novel training algorithm for computationally intelligent architecture...
[[abstract]]This paper presents a stability method which is based on the stability condition of slid...
The paper is concerned with the application of quadratic optimization for motion control to feedback...
In this work possibility of improvement of algorithms of neural control of anthropomorphic manipulat...
This paper discusses the stabilizability of arti®cial neural networks trained by utilizing the gradi...
Abstract—In this paper, a stabilization method based on the input–output conicity criterion is prese...
In this work, a novel and model-based artificial neural network (ANN) training method is developed s...
We aim at the optimization of the tracking control of a robot to improve the robustness, under the e...
67 p.Neural networks are widely used in industry fields, like robotic and process controllers. Exten...
The stability of learning rate in neural network identifiers and controllers is one of the challengi...
A robust neural network is proposed for use with a proportional fixed control scheme for robot contr...
Recurrent Neural Network (RNN) is a powerful tool for both theoretical modelling and practical appli...
Improving adversarial robustness of neural networks remains a major challenge. Fundamentally, traini...
grantor: University of TorontoAn artificial neural network (ANN) control method is develop...
To solve the problem of convergence to a local optimum in the multi-layer feedforward neural network...
Abstract—This paper presents a novel training algorithm for computationally intelligent architecture...
[[abstract]]This paper presents a stability method which is based on the stability condition of slid...
The paper is concerned with the application of quadratic optimization for motion control to feedback...
In this work possibility of improvement of algorithms of neural control of anthropomorphic manipulat...