A new approach to artificial neural networks

Filho, B.D. Baptista; Cabral, Eduardo Lobo Lustosa; Soares, A.J.

doi:10.1109/72.728360

Cited by 10 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep Learning is a subset of machine learning that utilizes neural network models for learning. The basic principle of deep learning is to simulate the neural network of the human brain by constructing a multi-layer neural network to learn and form more abstract highlevel representation attribute classes or features by combining low-level features to discover distributed feature representations of data [8]. The effectiveness of deep learning was not much realizable because of the lack of training data until the rise of big data eliminated the impact of "over-fitting".…”

Section: Introductionmentioning

confidence: 99%

Artificial Intelligence in the 21st Century

Gong

2023

Res Intell Manuf Assem

View full text Add to dashboard Cite

Artificial intelligence (AI) is the most important and interesting technology in the 21st Century due to its vast application. This review focuses on the evolution of AI techniques and their applications in recent decades. Deep learning algorithms/models, represented by Large Language Models (LLMs) have resulted in groundbreaking advancements, indicating that AI is evolving to improve its capacity to interact with and help people in various fields such as finance, medicine, and science research. The potential for research in AI is immense, and there is a need for scientific principles behind AI. Future perspectives on how machines can be developed to work with humans and to be compatible with human values and preferences are also discussed.

show abstract

Section: Introductionmentioning

confidence: 99%

Artificial Intelligence in the 21st Century

Gong

2023

Res Intell Manuf Assem

View full text Add to dashboard Cite

show abstract

“…One can find a number of applications in control system using neural network which explains various neural network approaches. Various neural network approaches in control applications are available in literatures [8,9,10,11,12]. In all these applications , neural networks can be trained by using different techniques as explained in [13,14,15,16].…”

Section: Introductionmentioning

confidence: 99%

ANN based adaptive controller tuned by RTRL algorithm for non-linear systems

Thampatty

Nandakumar

Cheriyan

2009

2009 2nd International Workshop on Nonlinear Dynamics and Synchronization

View full text Add to dashboard Cite

The paper presents artificial neural network (ANN) based adaptive controller for nonlinear systems. A state feedback adaptive control algorithm using fully connected recurrent neural network is employed. The desired trajectory for the on-line training of the neural network is obtained from a reference model. The synaptic weights adaptation of the network is based on real time recurrent learning algorithm (RTRL). Since the synaptic weights are adjusted in real time, this novel method of controller design has potential applications in non-linear systems. Simulation results of the controller applied to a simple non-linear dynamic system demonstrate the effectiveness of the controller.Index Terms-Artificial neural network (ANN), Non-linear control system, Real time recurrent learning algorithm (RTRL).

show abstract

“…They suggested two extended models of SISO neurocontroller to realize multivariable systems for identification and control, in which the controls are generated by training the unknown models with available inputoutput data. Different control strategies [6], [8], [11], [16] and [19] .using neural network with different training methods like feed forward architecture with back propagation learning algorithm [3] are available in literature A methodology to develop a proper model for the design of a robust controller for multivariable system is explained in [17], where the controller is In most of the training techniques, retaining the information about the infinite past are not possible, which is a drawback for the real-time applications. In feed forward neural networks, back propagation with adaptive learning rate is the most widely used gradient based algorithm.…”

Section: Introductionmentioning

confidence: 99%

RTRL Algorithm Based Adaptive Controller for Non-linear Multivariable Systems

Thampatty¹,

Nandakumar²,

Cheriyan³

2010

IJCA

View full text Add to dashboard Cite

The paper presents a new design of adaptive and dynamic neural network-based controller architecture with feedback connection for non-linear multivariable systems. The network is trained online at each sampling interval using the desired output trajectory and the training method used is the Real Time Recurrent Learning Algorithm (RTRL). The recurrent network is a fully connected one, with feedback from output layer to the input layer through a delay element. Since the synaptic weights to the neurons are adjusted on-line, this controller has potential applications in real time control also. Moreover, it can be used for both continuous and discrete systems. The simulation results obtained by applying the algorithm to a non-linear multivariable system demonstrate the effectiveness of the proposed method.

show abstract

A new approach to artificial neural networks

Cited by 10 publications

References 18 publications

Artificial Intelligence in the 21st Century

Artificial Intelligence in the 21st Century

ANN based adaptive controller tuned by RTRL algorithm for non-linear systems

RTRL Algorithm Based Adaptive Controller for Non-linear Multivariable Systems

Contact Info

Product

Resources

About