• The Journal of the Convergence on Culture Technology
• /
• v.9 no.1
• /
• pp.649-654
• /
• 2023

This paper proposes the design of a neural network structure search model using graph convolutional neural networks. Deep learning has a problem of not being able to verify whether the designed model has a structure with optimized performance due to the nature of learning as a black box. The neural network structure search model is composed of a recurrent neural network that creates a model and a convolutional neural network that is the generated network. Conventional neural network structure search models use recurrent neural networks, but in this paper, we propose GC-NAS, which uses graph convolutional neural networks instead of recurrent neural networks to create convolutional neural network models. The proposed GC-NAS uses the Layer Extraction Block to explore depth, and the Hyper Parameter Prediction Block to explore spatial and temporal information (hyper parameters) based on depth information in parallel. Therefore, since the depth information is reflected, the search area is wider, and the purpose of the search area of the model is clear by conducting a parallel search with depth information, so it is judged to be superior in theoretical structure compared to GC-NAS. GC-NAS is expected to solve the problem of the high-dimensional time axis and the range of spatial search of recurrent neural networks in the existing neural network structure search model through the graph convolutional neural network block and graph generation algorithm. In addition, we hope that the GC-NAS proposed in this paper will serve as an opportunity for active research on the application of graph convolutional neural networks to neural network structure search.

• Journal of Institute of Control, Robotics and Systems
• /
• v.10 no.12
• /
• pp.1295-1304
• /
• 2004

In this paper, the Bayesian recurrent neural network is proposed to predict time series data. A neural network predictor requests proper learning strategy to adjust the network weights, and one needs to prepare for non-linear and non-stationary evolution of network weights. The Bayesian neural network in this paper estimates not the single set of weights but the probability distributions of weights. In other words, the weights vector is set as a state vector of state space method, and its probability distributions are estimated in accordance with the particle filtering process. This approach makes it possible to obtain more exact estimation of the weights. In the aspect of network architecture, it is known that the recurrent feedback structure is superior to the feedforward structure for the problem of time series prediction. Therefore, the recurrent neural network with Bayesian inference, what we call Bayesian recurrent neural network (BRNN), is expected to show higher performance than the normal neural network. To verify the proposed method, the time series data are numerically generated and various kinds of neural network predictor are applied on it in order to be compared. As a result, feedback structure and Bayesian learning are better than feedforward structure and backpropagation learning, respectively. Consequently, it is verified that the Bayesian reccurent neural network shows better a prediction result than the common Bayesian neural network.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.335-338
• /
• 2017

Currently Artificial Inteligence and Deep Learning are social issues, and These technologies are applied to various fields. A good method among the various algorithms in Artificial Inteligence is Convolutional Neural Network. Convolutional Neural Network is a form that adds convolution layers that extracts features by convolution operation on a general neural network method. If you use Convolutional Neural Network as small amount of data, or if the structure of layers is not complicated, you don't have to pay attention to speed. But the learning time is long as the size of the learning data is large and the structure of layers is complicated. So, GPU-based parallel processing is a lot. In this paper, we developed Convolutional Neural Network using CUDA and Learning speed is faster and more efficient than the method using the CPU.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.631-634
• /
• 2004

In this paper, the Bayesian recurrent neural network (BRNN) is proposed to predict time series data. Among the various traditional prediction methodologies, a neural network method is considered to be more effective in case of non-linear and non-stationary time series data. A neural network predictor requests proper learning strategy to adjust the network weights, and one need to prepare for non-linear and non-stationary evolution of network weights. The Bayesian neural network in this paper estimates not the single set of weights but the probability distributions of weights. In other words, we sets the weight vector as a state vector of state space method, and estimates its probability distributions in accordance with the Bayesian inference. This approach makes it possible to obtain more exact estimation of the weights. Moreover, in the aspect of network architecture, it is known that the recurrent feedback structure is superior to the feedforward structure for the problem of time series prediction. Therefore, the recurrent network with Bayesian inference, what we call BRNN, is expected to show higher performance than the normal neural network. To verify the performance of the proposed method, the time series data are numerically generated and a neural network predictor is applied on it. As a result, BRNN is proved to show better prediction result than common feedforward Bayesian neural network.

• Proceedings of the KIEE Conference
• /
• 2003.11b
• /
• pp.171-174
• /
• 2003

In this paper, a Learning module for a reconfigurable neural network processor(ERNIE) was proposed for an On-chip learning. The existing reconfigurable neural network processor(ERNIE) has a much better performance than the software program but it doesn't support On-chip learning function. A learning module which is based on Back Propagation algorithm was designed for a help of this weak point. A pipeline structure let the learning module be able to update the weights rapidly and continuously. It was tested with five types of alphabet font to evaluate learning module. It compared with C programed neural network model on PC in calculation speed and correctness of recognition. As a result of this experiment, it can be found that the neural network processor(ERNIE) with learning module decrease the neural network training time efficiently at the same recognition rate compared with software computing based neural network model. This On-chip learning module showed that the reconfigurable neural network processor(ERNIE) could be a evolvable neural network processor which can fine the optimal configuration of network by itself.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.3
• /
• pp.463-468
• /
• 2020

Artificial intelligence researches are being applied and developed in various fields. In this paper, we build a neural network by using the method of implementing artificial intelligence in the form of spiking natural networks (SNN), the next-generation of artificial intelligence research, and analyze how the number of neurons in that neural networks affect the performance of the neural networks. We also analyze how the performance of neural networks changes while increasing the amount of neural network learning. The findings will help optimize SNN-based neural networks used in each field.

• Journal of Korean Society of Forest Science
• /
• v.84 no.1
• /
• pp.63-70
• /
• 1995

This paper discusses applications of neural network to stand stocking control problems. The scope of this research was to develop a neural network model for finding optimal stand management regimes and examining the performance of the model for field application. Performance was analyzed in consideration of the number of training examples and structural aspects of neural network. Research on network performance was based on extensive optimization studies for pure longleaf pine(Pinus palustris) stands. For experimental purposes. an existing nonlinear even-aged stand optimization model with a whole-stand growth and yield simulator was used to generate data samples required for the performance analysis.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.36 no.2
• /
• pp.88-95
• /
• 1994

This paper is to evaluate the applicability of neural networks to the estimation of evapotranspiration. Two neural networks were developed to forecast daily evapotranspiration of the rice crop with back-propagation and counter-propagation algorithm. The neural network trained by back-propagation algorithm with delta learning rule is a three-layer network with input, hidden, and output layers. The other network with counter-propagation algorithm is a four-layer network with input, normalizing, competitive, and output layers. Training neural networks was conducted using daily actual evapotranspiration of rice crop and daily climatic data such as mean temperature, sunshine hours, solar radiation, relative humidity, and pan evaporation. During the training, neural network parameters were calibrated. The trained networks were applied to a set of field data not used in the training. The created response of the back-propagation network was in good agreement with desired values and showed better performances than the counter-propagation network did. Evaluating the neural network performance indicates that the back-propagation neural network may be applied to the estimation of evapotranspiration of the rice crop. This study does not provide with a conclusive statement as to the ability of a neural network to evapotranspiration estimating. More detailed study is required for better understanding and evaluating the behavior of neural networks.

• ETRI Journal
• /
• v.41 no.6
• /
• pp.760-770
• /
• 2019

Based on the growing demand for neural network technologies, various neural network inference engines are being developed. However, each inference engine has its own neural network storage format. There is a growing demand for standardization to solve this problem. This study presents interworking techniques for ensuring the compatibility of neural networks and data among the various deep learning frameworks. The proposed technique standardizes the graphic expression grammar and learning data storage format using the Neural Network Exchange Format (NNEF) of Khronos. The proposed converter includes a lexical, syntax, and parser. This NNEF parser converts neural network information into a parsing tree and quantizes data. To validate the proposed system, we verified that MNIST is immediately executed by importing AlexNet's neural network and learned data. Therefore, this study contributes an efficient design technique for a converter that can execute a neural network and learned data in various frameworks regardless of the storage format of each framework.

• International Journal of Control, Automation, and Systems
• /
• v.6 no.1
• /
• pp.24-34
• /
• 2008

A novel neural network model, termed the standard neural network model (SNNM), similar to the nominal model in linear robust control theory, is suggested to facilitate the synthesis of controllers for delayed (or non-delayed) nonlinear systems composed of neural networks. The model is composed of a linear dynamic system and a bounded static delayed (or non-delayed) nonlinear operator. Based on the global asymptotic stability analysis of SNNMs, Static state-feedback controller and dynamic output feedback controller are designed for the SNNMs to stabilize the closed-loop systems, respectively. The control design equations are shown to be a set of linear matrix inequalities (LMIs) which can be easily solved by various convex optimization algorithms to determine the control signals. Most neural-network-based nonlinear systems with time delays or without time delays can be transformed into the SNNMs for controller synthesis in a unified way. Two application examples are given where the SNNMs are employed to synthesize the feedback stabilizing controllers for an SISO nonlinear system modeled by the neural network, and for a chaotic neural network, respectively. Through these examples, it is demonstrated that the SNNM not only makes controller synthesis of neural-network-based systems much easier, but also provides a new approach to the synthesis of the controllers for the other type of nonlinear systems.