• Journal of Semiconductor Engineering
• /
• v.2 no.1
• /
• pp.125-129
• /
• 2021

As the interest of deep learning, techniques to control the color of images in image processing field are evolving together. However, there is no clear standard for color, and it is not easy to find a way to represent only the color itself like the color-palette. In this paper, we propose a novel color palette extraction system by chroma fine-tuning with reinforcement learning. It helps to recognize the color combination to represent an input image. First, we use RGBY images to create feature maps by transferring the backbone network with well-trained model-weight which is verified at super resolution convolutional neural networks. Second, feature maps are trained to 3 fully connected layers for the color-palette generation with a generative adversarial network (GAN). Third, we use the reinforcement learning method which only changes chroma information of the GAN-output by slightly moving each Y component of YCbCr color gamut of pixel values up and down. The proposed method outperforms existing color palette extraction methods as given the accuracy of 0.9140.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.5
• /
• pp.353-360
• /
• 2004

This paper considers reinforcement learning control with the self-organizing map. Reinforcement learning uses the observable states of objective system and signals from interaction of the system and environment as input data. For fast learning in neural network training, it is necessary to reduce learning data. In this paper, we use the self-organizing map to partition the observable states. Partitioning states reduces the number of learning data which is used for training neural networks. And neural dynamic programming design method is used for the controller. For evaluating the designed reinforcement learning controller, an inverted pendulum on the cart system is simulated. The designed controller is composed of serial connection of self-organizing map and two Multi-layer Feed-Forward Neural Networks.

• Journal of Institute of Control, Robotics and Systems
• /
• v.2 no.2
• /
• pp.108-114
• /
• 1996

We present proofs of the stability and convergence of Self-organizing feature map (SOFM) neural network with time-invarient learning rate and binary reinforcement function. One of the major problems in Self-organizing feature map neural network concerns with learning rate-"Kalman Filter" gain in stochsatic control field which is monotone decreasing function and converges to 0 for satisfying minimum variance property. In this paper, we show that the stability and convergence of Self-organizing feature map neural network with time-invariant learning rate. The analysis of the proposed algorithm shows that the stability and convergence is guranteed with exponentially stable and weak convergence properties as well.s as well.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2018.07a
• /
• pp.47-48
• /
• 2018

본 논문에서는 NP-hard 문제로 알려진 잡샵 스케쥴링에 대하여 강화학습적 측면에서 접근하는 방식에 대해 제안한다. 다양한 시간이 소요되는 업무들이 가지는 특징들을 최대한 state space aggregation에 고려하고, 이를 neural network를 통해 최적화 시간을 줄이는 방식이다. 잡샵 스케쥴링에 대한 솔루션은 미래에 대한 예측이 불가능하고 다양한 시간이 소요되는 스케쥴링 문제를 최적화하는 것에 대한 가능성을 제시할 것으로 기대된다.

• The Journal of Korea Robotics Society
• /
• v.18 no.3
• /
• pp.352-357
• /
• 2023

Since robotic assembly in an unstructured environment is very difficult with existing control methods, studies using artificial intelligence such as reinforcement learning have been conducted. However, since long-time operation of a robot for learning in the real environment adversely affects the robot, so a method to shorten the learning time is needed. To this end, a method based on a pre-trained neural network was proposed in this study. This method showed a learning speed about 3 times than the existing methods, and the stability of reward during learning was also increased. Furthermore, it can generate a more optimal policy than not using a pre-trained neural network. Using the proposed reinforcement learning-based assembly trajectory generator, 100 attempts were made to assemble the power connector within a random error of 4.53 mm in width and 3.13 mm in length, resulting in 100 successes.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1997.11a
• /
• pp.120-123
• /
• 1997

In this paper, we propose the Fuzzy Inference-based Reinforcement Learning Algorithm. We offer more similar learning scheme to the psychological learning of the higher animal's including human, by using Fuzzy Inference in Reinforcement Learning. The proposed method follows the way linguistic and conceptional expression have an effect on human's behavior by reasoning reinforcement based on fuzzy rule. The intervals of fuzzy membership functions are found optimally by genetic algorithms. And using Recurrent state is considered to make an action in dynamical environment. We show the validity of the proposed learning algorithm by applying to the inverted pendulum control problem.

• Journal of Korea Multimedia Society
• /
• v.21 no.8
• /
• pp.969-981
• /
• 2018

Recent advances in machine learning approaches such as deep neural network and reinforcement learning offer significant performance improvements in generating detailed and varied motions in physically simulated virtual environments. The optimization methods are highly attractive because it allows for less understanding of underlying physics or mechanisms even for high-dimensional subtle control problems. In this paper, we propose an efficient learning method for stochastic policy represented as deep neural networks so that agent can generate various energetic motions adaptively to the changes of tasks and states without losing interactivity and robustness. This strategy could be realized by our novel trajectory search method motivated by the trust region policy optimization method. Our value-based trajectory smoothing technique finds stably learnable trajectories without consulting neural network responses directly. This policy is set as a trust region of the artificial neural network, so that it can learn the desired motion quickly.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.10
• /
• pp.23-31
• /
• 2018

Recently, there have been many studies on machine learning. Among them, studies on reinforcement learning are actively worked. In this study, we propose a controller to control bicycle using DDPG (Deep Deterministic Policy Gradient) algorithm which is the latest deep reinforcement learning method. In this paper, we redefine the compensation function of bicycle dynamics and neural network to learn agents. When using the proposed method for data learning and control, it is possible to perform the function of not allowing the bicycle to fall over and reach the further given destination unlike the existing method. For the performance evaluation, we have experimented that the proposed algorithm works in various environments such as fixed speed, random, target point, and not determined. Finally, as a result, it is confirmed that the proposed algorithm shows better performance than the conventional neural network algorithms NAF and PPO.

• Journal of Industrial Technology
• /
• v.20 no.B
• /
• pp.201-206
• /
• 2000

A priori information of object is needed to control in some well known control methods. But we can't always know a priori information of object in real world. In this paper, the inverted pendulum is simulated as a control task with the goal of learning to balance the pendulum with no a priori information using neural network controller. In contrast to other applications of neural networks to the inverted pendulum task, the performance feedback is unavailable on each training step, appearing only as a failure signal when the pendulum falls or reaches the bound of track. To solve this task, the delayed performance evaluation and the learning of nonlinear of nonlinear functions must be dealt. Reinforcement learning method is used for those issues.

• Journal of the Korean Society for Precision Engineering
• /
• v.13 no.4
• /
• pp.75-86
• /
• 1996

In this paper, we propose a new fuzzy-neural network control scheme for the speed and azimuth control of a mobile robot. The proposed control scheme uses a gaussian function as a unit function in the fuzzy-neural network, and back propagation algorithm to train the fuzzy-neural network controller in the frame-work of the specialized learning architecture. It is proposed a learning controller consisting of two fuzzy-neural networks based on independent reasoning and a connection net woth fixed weights to simply the fuzzy-neural network. The effectiveness of the proposed controller is illustrated by performing the computer simulation for a circular trajectory tracking of a mobile robot driven by two independent wheels.