• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.4
• /
• pp.395-399
• /
• 2005

In this paper, we presents HIGH-Q learning algorithm with reinforcement learning for more fast and exact topic-directed web spidering. The purpose of reinforcement learning is to maximize rewards from environment, an reinforcement learning agents learn by interacting with external environment through trial and error. We performed experiments that compared the proposed method using reinforcement learning with breath first search method for searching the web pages. In result, reinforcement learning method using future discounted rewards searched a small number of pages to find result pages.

• Journal of KIISE:Software and Applications
• /
• v.28 no.9
• /
• pp.603-611
• /
• 2001

This paper proposes a novel fast layer-by-layer algorithm that has better generalization capability. In the proposed algorithm, the weights of the hidden layer are updated by the target vector of the hidden layer obtained by least squares method. The proposed algorithm improves the learning speed that can occur due to the small magnitude of the gradient vector in the hidden layer. This algorithm was tested in a handwritten digits recognition problem. The learning speed of the proposed algorithm was faster than those of error back propagation algorithm and modified error function algorithm, and similar to those of Ooyen's method and layer-by-layer algorithm. Moreover, the simulation results showed that the proposed algorithm had the best generalization capability among them regardless of the number of hidden nodes. The proposed algorithm has the advantages of the learning speed of layer-by-layer algorithm and the generalization capability of error back propagation algorithm and modified error function algorithm.

• Geophysics and Geophysical Exploration
• /
• v.22 no.4
• /
• pp.202-209
• /
• 2019

In this study, an acoustic full-waveform inversion using Adam optimizer was proposed. The steepest descent method, which is commonly used for the optimization of seismic waveform inversion, is fast and easy to apply, but the inverse problem does not converge correctly. Various optimization methods suggested as alternative solutions require large calculation time though they were much more accurate than the steepest descent method. The Adam optimizer is widely used in deep learning for the optimization of learning model. It is considered as one of the most effective optimization method for diverse models. Thus, we proposed seismic full-waveform inversion algorithm using the Adam optimizer for fast and accurate convergence. To prove the performance of the suggested inversion algorithm, we compared the updated P-wave velocity model obtained using the Adam optimizer with the inversion results from the steepest descent method. As a result, we confirmed that the proposed algorithm can provide fast error convergence and precise inversion results.

• Journal of Digital Contents Society
• /
• v.19 no.1
• /
• pp.35-41
• /
• 2018

The Q-learning algorithm based on reinforcement learning is useful for learning the goal for one behavior at a time, using a combination of discrete states and actions. In order to learn multiple actions, applying a behavior-based architecture and using an appropriate behavior adjustment method can make a robot perform fast and reliable actions. Q-learning is a popular reinforcement learning method, and is used much for robot learning for its characteristics which are simple, convergent and little affected by the training environment (off-policy). In this paper, Q-learning algorithm is applied to a lamp robot to learn multiple behaviors (human recognition, desk object recognition). As the learning rate of Q-learning may affect the performance of the robot at the learning stage of multiple behaviors, we present the optimal multiple behaviors learning model by changing learning rate.

• Journal of information and communication convergence engineering
• /
• v.9 no.6
• /
• pp.637-640
• /
• 2011

The hybrid neural networks have characteristics such as fast learning times, generality, and simplicity, and are mainly used to classify learning data and to model non-linear systems. The middle layer of a hybrid neural network clusters the learning vectors by grouping homogenous vectors in the same cluster. In the clustering procedure, the homogeneity between learning vectors is represented as the distance between the vectors. Therefore, if the distances between a learning vector and all vectors in a cluster are smaller than a given constant radius, the learning vector is added to the cluster. However, the usage of a constant radius in clustering is the primary source of errors and therefore decreases the recognition success rate. To improve the recognition success rate, we proposed the enhanced hybrid network that organizes the middle layer effectively by using the enhanced ART1 network adjusting the vigilance parameter dynamically according to the similarity between patterns. The results of experiments on a large number of calling card images showed that the proposed algorithm greatly improves the character extraction and recognition compared with conventional recognition algorithms.

• The Korean Journal of Applied Statistics
• /
• v.15 no.2
• /
• pp.251-267
• /
• 2002

Self Organizing Maps(SOM) by Kohonen is very fast algorithm in neural networks. But it doesn't show sure rules of training results. In this paper, we introduce to Bayesian Learning for Self Organizing Maps(BLSOM) which combines self organizing maps with Bayesian learning. So it supports explanatory power of models and improves prediction. BLSOM has global optima anywhere but SOM has not. This is proved by experiment in this paper.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.2
• /
• pp.127-134
• /
• 2004

In this paper, human motor behaving model based sensory motor coordination(SMC) algorithm is implemented on robotic grasping task. Compare to conventional SMC models which connect sensor to motor directly, the proposed method used biologically inspired human behaving system in conjunction with SMC algorithm for fast grasping force control of robot arm. To characterize various grasping objects, pressure sensors on hand gripper were used. Measured sensory data are simultaneously transferred to perceptual mechanism(PM) and long term memory(LTM), and then the sensory information is forwarded to the fastest channel among several information-processing flows in human motor system. In this model, two motor learning routes are proposed. One of the route uses PM and the other uses short term memory(STM) and LTM structure. Through motor learning procedure, successful information is transferred from STM to LTM. Also, LTM data are used for next moor plan as reference information. STM is designed to single layered perception neural network to generate fast motor plan and receive required data which comes from LTM. Experimental results showed that proposed method can control of the grasping force adaptable to various shapes and types of greasing objects, and also it showed quicker grasping-behavior lumining time compare to simple feedback system.

• Proceedings of the IEEK Conference
• /
• 2002.07a
• /
• pp.698-701
• /
• 2002

Subspace analysis (which includes PCA) seeks for feature subspace (which corresponds to the eigenspace), given multivariate input data and has been widely used in computer vision and pattern recognition. Typically data space belongs to very high dimension, but only a few principal components need to be extracted. In this paper I present a fast sequential algorithm for subspace analysis or tracking. Useful behavior of the algorithm is confirmed by numerical experiments.

• Journal of the Korea Convergence Society
• /
• v.5 no.4
• /
• pp.163-169
• /
• 2014

A stable neural network control scheme for unknown non-linear systems is developed in this paper. While the control variable is optimised to minimize the performance index, convergence of the index is guaranteed asymptotically stable by a Lyapnov control law. The optimization is achieved using a gradient descent searching algorithm and is consequently slow. A fast convergence algorithm using an adaptive learning rate is employed to speed up the convergence. Application of the stable control to a single input single output (SISO) non-linear system is simulated. The satisfactory control performance is obtained.

• Proceedings of the IEEK Conference
• /
• 1998.06a
• /
• pp.705-708
• /
• 1998

In this paper, a new algorithm is proposed that the template matching is used to devide SOFM (self-organizig feature map) for fast learning and to extract features for considering input data types. In order to verify the superoprity of the proposed algorithm, applied to the recognition of handwritten numerals. Templates of handwritten numerals are created by a line of external-contact.