• 전기의세계
• /
• v.38 no.2
• /
• pp.23-30
• /
• 1989

과학기술의 고속화에 따라 종래에는 인간이 더 잘수행하던 지능을 요하는 일들이 점점 컴퓨터에 의해 처리되는 경우가 늘어나고 있다. 그러나 아직도 많은 분야에서 종래의 방식에 의한 한개의 processor나 몇개의 간단한 multiprocessor시스템으로는 너무 많은 시간이 걸려서 처리할 수 없는 일들이 산재해 있다. 예를 들어 image를 인식하는 것이나 언어습득과 번역과 같은 문제들에서 인간의 뇌가 현존하고 있는 어떤 컴퓨터의 성능보다 능가하는 것을 알고 있다. 그 이유는 근본적으로 디지탈 컴퓨터와 인간의 뇌 사이의 정보 처리방식이 틀린점에 기인한다. 대부분의 컴퓨터는 한개 또는 몇개의 main procrssor들이 자료들을 sequential하게 처리하는 데에 반하여, 인간의 뇌는 수천억 개의 neuron들이 정보를 병렬로 처리하고 있다. 따라서 인간의 뇌에 대한 깊이 연구와 그에 따른 새로운 형태의 정보처리 기술의 개발이 시급히 요구되어지고 있다. 최근에 이와같은 massive parallelism을 구현하기 위한 시도가 neural network를 중심으로 일어나고 있다. 여기에서 사용되는 algorithm들은 local information을 실현한다. Neural network에는 여러가지 model들이 있으나 본고에서는 optimization model을 중심으로 그 배경 및 응용을 소개하고자 한다.

• Journal of the Korea Computer Graphics Society
• /
• v.30 no.3
• /
• pp.81-86
• /
• 2024

The Image Signal Processor (ISP) converts RAW images captured by the camera sensor into user-preferred sRGB images. While RAW images contain more meaningful information for image processing than sRGB images, RAW images are rarely shared due to their large sizes. Moreover, the actual ISP process of a camera is not disclosed, making it difficult to model the inverse process. Consequently, research on learning the conversion between sRGB and RAW has been conducted. Recently, the ParamISP[1] model, which directly incorporates camera parameters (exposure time, sensitivity, aperture size, and focal length) to mimic the operations of a real camera ISP, has been proposed by advancing the simple network structures. However, existing studies, including ParamISP[1], have limitations in modeling the camera ISP as they do not consider the degradation caused by lens shading, optical aberration, and lens distortion, which limits the restoration performance. This study introduces Positional Encoding to enable the camera ISP neural network to better handle degradations caused by lens. The proposed positional encoding method is suitable for camera ISP neural networks that learn by dividing the image into patches. By reflecting the spatial context of the image, it allows for more precise image restoration compared to existing models.

• Journal of the Institute of Convergence Signal Processing
• /
• v.1 no.1
• /
• pp.1-6
• /
• 2000

In this paper, the hybrid system of HMM and neural network is proposed and show better recognition rate of the post-process procedure which minimizes the process error of recognition than that of HMM(Hidden Markov Model) only used. After the HMM training by training data, testing data that are not taken part in the training are sent to HMM. The output probability from HMM output by testing data is used for the training data of the neural network, post processor. After neural network training, the hybrid system is completed. This hybrid system makes the recognition rate improvement of about $4.5\%$ in MLP and about $2\%$ in RBFN and gives the solution to training time of conventional hybrid system and to decrease of the recognition rate due to the lack of training data in real-time speech recognition system.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.13 no.2
• /
• pp.55-62
• /
• 1999

In order to perform a elaborate task like as assembly, manufacturing and so forth of components, tracking control on the trajectory of power coming in contact with a target as well as tracking control on the movement course trajectory of end-effector is indispensable. In this paper, to bring under robust ard accurate control of auto-equipnent systems which disturbance, parameter alteration of system, uncertainty ard so forth exist, neural network controller called dynamic neural processor(DNP) is designed. Also, the learning architecture to compute inverse kinematic coordinates transfonnations in the manirclator of auto-equipnent systems is developed ard the example that DNP can be used is explained The architocture and learning algorithm of the proposed dynamic neural network, the DNP, are described and computer simllations are provided to demonstrate the effectiveness of the proposed learning method using the DNP.he DNP.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.6 no.1
• /
• pp.7-17
• /
• 1997

During the past decade, there were many well-established theories for the adaptive control of linear systems, but there exists relatively little general theory for the adaptive control of nonlinear systems. Adaptive control technique is essential for providing a stable and robust performance for application of industrial robot control. Neural network computing methods provide one approach to the development of adaptive and learning behavior in robotic system for manufacturing. Computational neural networks have been demonstrated which exhibit capabilities for supervised learning, matching, and generalization for problems on an experimental scale. Supervised learning could improve the efficiency of training and development of robotic systems. In this paper, a new scheme of adaptive-neuro control system to implement real-time control of robot manipulator using digital signal processors is proposed. Digital signal processors, DSPs, are micro-processors that are developed particularly for fast numerical computations involving sums and products of variables. The proposed neuro control algorithm is one of learning a model based error back-propagation scheme using Lyapunov stability analysis method. The proposed adaptive-neuro control scheme is illustrated to be an efficient control scheme for implementation of real-time control for SCARA robot with four-axes by experiment.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.10a
• /
• pp.416-419
• /
• 2003

The cellular neural networks have the circuit structure that differs from the form of general neural network. It consists of an array of the same cell which is a simple processing element, and each of the cells has local connectivity and space invariant template property. In this paper, time-multiplex image processing technique is applied for processing large images using small size CNN cell block, and we simulate the edge detection of a large image using the simulator implemented with a c program and matlab model. A 5$\times$5 CNN hardware and pre post processor is also implemented and is under test.

• The Journal of the Acoustical Society of Korea
• /
• v.36 no.6
• /
• pp.425-435
• /
• 2017

In this paper, we propose optimization methods for speeding the feedforward network of deep neural networks using NEON SIMD (Single Instruction Multiple Data) parallel instructions and multi-core parallelization on the multi-core ARM processor. As the result of the optimization using SIMD parallel instructions, we present the amount of speed improvement and arithmetic precision stage by stage. Through the optimization using SIMD parallel instructions on the single core, we obtain $2.6{\times}$ speedup over the baseline implementation using C compiler. Furthermore, by parallelizing the single core implementation on the multi-core, we obtain $5.7{\times}{\sim}7.7{\times}$ speedup. The results we obtain show the possibility for applying the arithmetic-intensive deep neural network technology to applications on mobile devices.

• The KIPS Transactions:PartB
• /
• v.9B no.4
• /
• pp.429-436
• /
• 2002

In order to apply the artificial neural network to the practical application, it is needed to implement it with the hardware system. It is most promising to make it with the hybrid VLSI among various possible technologies. When we Implement a trained network into the hybrid neuro-chips, it is to be performed the process of the quantization on its neuron outputs and its weights. Unfortunately this process cause the network's outputs to be distorted from the original trained outputs. In this paper we analysed in detail the statistical characteristics of the distortion. The analysis implies that the network is to be trained using the normalized input patterns and finally into the solution with the small weights to reduce the distortion of the network's outputs. We performed the experiment on an application in the time series prediction area to investigate the effectiveness of the results of the analysis. The experiment showed that the network by our method has more smaller distortion compared with the regular network.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2002.04a
• /
• pp.387-392
• /
• 2002

This paper presents a new scheme of neural network controller to improve the robustuous of robot manipulator using digital signal processors. Digital signal processors, DSPs, are micro-processors that are particularly developed for fast numerical computations involving sums and products of variables. Digital version of most advanced control algorithms can be defined as sums and products of measured variables, thus it can be programmed and executed through DSPs. In addition, DSPs are as fast in computation as most 32-bit micro-processors and yet at a fraction of their prices. These features make DSPs a viable computational tool in digital implementation of sophisticated controllers. During past decade it was proposed the well-established theorys for the adaptive control of linear systems, but there exists relatively little general theory for the adaptive control of nonlinear systems. Perforating of the proposed controller is illustrated. This paper describes a new approach to the design of adaptive controller and implementation of real-time control for assembling robotic manipulator using digital signal processor. Digital signal processors used in implementing real time adaptive control algorithm are TMS320C50 series made in TI'Co..

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2001.10a
• /
• pp.134-139
• /
• 2001

This paper presents a new scheme of neural network controller to improve the robustuous of robot manipulator using digital signal processors. Digital signal processors, DSPs, are micro-processors that are particularly developed for fast numerical computations involving sums and products of variables. Digital version of most advanced control algorithms can be defined as sums and products of measured variables, thus it can be programmed and executed through DSPs. In addition, DSPs are as fast in computation as most 32-bit micro-processors and yet at a fraction of their prices. These features make DSPs a viable computational tool in digital implementation of sophisticated controllers. During past decade it was proposed the well-established theorys for the adaptive control of linear systems, but there exists relatively little general theory for the adaptive control of nonlinear systems. Perforating of the proposed controller is illustrated. This paper describes a new approach to the design of adaptive controller and implementation of real-time control for assembling robotic manipulator using digital signal processor. Digital signal processors used in implementing real time adaptive control algorithm are TMS320C50 series made in TI'Co..