• Journal of Digital Convergence
• /
• v.17 no.10
• /
• pp.251-258
• /
• 2019

In the future, various products are created in various fields using artificial intelligence. In this age, it is a very important problem to know the operation principle of artificial intelligence learning method and to use it correctly. This paper introduces artificial intelligence learning methods that have been known so far. Learning of artificial intelligence is based on the fixed point iteration method of mathematics. The GD(Gradient Descent) method, which adjusts the convergence speed based on the fixed point iteration method, the Momentum method to summate the amount of gradient, and finally, the Adam method that mixed these methods. This paper describes the advantages and disadvantages of each method. In particularly, the Adam method having adaptivity controls learning ability of machine learning. And we analyze how these methods affect digital signals. The changes in the learning process of digital signals are the basis of accurate application and accurate judgment in the future work and research using artificial intelligence.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.9
• /
• pp.1679-1687
• /
• 2016

Mobile robots are effectively used in industrial fields that require flexible manufacturing systems. Mobile robots have to move with mechanical loads such as product parts along the specified paths, and are usually equipped with kinematic controllers. When the loads and nonlinear frictions are too high, satisfactory control performances can not be expected with the kinematic controllers, so some dynamic controllers have been developed. Conventional dynamic controllers require the exact weights and locations of the loads; however, the loads are frequently changed and unknown so that the control performances of the conventional controllers are limited. This paper proposes an adaptive PD control method using gradient descent learning to have sufficient dynamic control performance for unknown loads. Simulation studies have been conducted for various load conditions to verify that the adaptive PD control method have much broader convergence region than the convention method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.3
• /
• pp.505-513
• /
• 2009

Z. Cao had proposed NFRM(new fuzzy reasoning method) which infers in detail using relation matrix. In spite of the small inference rules, it shows good performance than mamdani's fuzzy inference method. But the most of fuzzy systems are difficult to make fuzzy inference rules in the case of MIMO system. The past days, We had proposed the MIMO fuzzy inference which had extended a Z. Cao's fuzzy inference to handle MIMO system. But many times and effort needed to determine the relation matrix elements of MIMO fuzzy inference by heuristic and trial and error method in order to improve inference performances. In this paper, we propose a MIMO fuzzy inference method with the learning ability witch is used a gradient descent method in order to improve the performances. Through the computer simulation studies for the inverse kinematics problem of 2-axis robot, we show that proposed inference method using a gradient descent method has good performances.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.12
• /
• pp.2418-2425
• /
• 1994

Although the error backpropagation(EBP) algorithm based on the gradient descent method is a widely-used learning algorithm of neural networks, learning sometimes takes a long time to acquire accuracy. This paper develops a novel learning method to alleviate the problems of EBP algorithm such as local minima, slow speed, and size of structure and thus to improve performance by adopting other new networks. Gaussian Potential Function networks(GPFN), in parallel with multilayer neural networks. Empirical simulations show the efficacy of the proposed algorithm in function approximation, which enables us to train networks faster with the better generalization capabilities.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.6
• /
• pp.505-514
• /
• 2020

Since a large amount of training data is typically needed to train Deep Neural Networks (DNNs), a parallel training approach is required to train the DNNs. The Stochastic Gradient Descent (SGD) algorithm is one of the most widely used methods to train the DNNs. However, since the SGD is an inherently sequential process, it requires some sort of approximation schemes to parallelize the SGD algorithm. In this paper, we review various efforts on parallelizing the SGD algorithm, and analyze the computational overhead, communication overhead, and the effects of the approximations.

• Proceedings of the IEEK Conference
• /
• 1999.06a
• /
• pp.1033-1036
• /
• 1999

This paper proposes an efficient fault diagnosis for digital circuits using multilayer neural networks. The efficient learning algorithm is also proposed for the multilayer neural network, which is combined the steepest descent for high-speed optimization and the dynamic tunneling for global optimization. The fault-diagnosis system using the multilayer neural network of the proposed algorithm has been applied to the parity generator circuit. The simulation results shows that the proposed system is higher convergence speed and rate, in comparision with system using the backpropagation algorithm based on the gradient descent.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.05a
• /
• pp.193-196
• /
• 2008

Z. Cao had proposed NFRM(new fuzzy reasoning method) which infers in detail using relation matrix. In spite of the small inference rules, it shows good performance than mamdani's fuzzy inference method. In this paper, we propose 2. Cao's fuzzy inference method using learning ability witch is used a gradient descent method in order to improve the performances. Because it is difficult to determine the relation matrix elements by trial and error method which is needed many hours and effort. Simulation results are applied linear and nonlinear system show that the proposed inference method has good performances.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.316-321
• /
• 2003

This paper presents a design method of the wavelet neural network based controller using direct adaptive control method to deal with a stable intelligent control of chaotic systems. The various uncertainties, such as mechanical parametric variation, external disturbance, and unstructured uncertainty influence the control performance. However, the conventional control methods such as optimal control, adaptive control and robust control may not be feasible when an explicit, faithful mathematical model cannot be constructed. Therefore, an intelligent control system that is an on-line trained WNN controller based on direct adaptive control method with adaptive learning rates is proposed to control chaotic nonlinear systems whose mathematical models are not available. The adaptive learning rates are derived in the sense of discrete-type Lyapunov stability theorem, so that the convergence of the tracking error can be guaranteed in the closed-loop system. In the whole design process, the strict constrained conditions and prior knowledge of the controlled plant are not necessary due to the powerful learning ability of the proposed intelligent control system. The gradient-descent method is used for training a wavelet neural network controller of chaotic systems. Finally, the effectiveness and feasibility of the proposed control method is demonstrated with application to the chaotic systems.

• Korean Journal of Cognitive Science
• /
• v.4 no.2
• /
• pp.181-200
• /
• 1994

In the learning phase of multilyer feedforword neural network,there are problems such that local minimum,learning praralysis and slow learning speed when backpropagation algorithm used.To overcome these problems, the genetic algorithm has been used as learing method in the multilayer feedforword neural network instead of backpropagation algorithm.However,because the genetic algorith, does not have any mechanism for fine-tuned local search used in backpropagation method,it takes more time that the genetic algorithm converges to a global optimal solution.In this paper,we suggest a new GA-BP method which provides a fine-tunes local search to the genetic algorithm.GA-BP method uses gradient descent method as one of genetic algorithm's operators such as mutation or crossover.To show the effciency of the developed method,we applied it to the 3-parity bit problem with analysis.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.5
• /
• pp.1125-1132
• /
• 2017

In a situation where the severity and frequency of drought events getting stronger and higher, many studies related to drought forecast have been conducted to improve the drought forecast accuracy. However it is difficult to predict drought events using a single model because of nonlinear and complicated characteristics of temporal behavior of drought events. In this study, in order to overcome the shortcomings of the single model approach, we first build various single models capable to explain the relationship between the meteorological drought index, Standardized Precipitation Index (SPI), and other independent variables such as world climate indices. Then, we developed a combined models using Stochastic Gradient Descent method among Ensemble Learnings.