• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.2
• /
• pp.53.4-53.4
• /
• 2019

We reconstruct the underlying dark matter (DM) density distribution of the local universe within 20Mpc/h cubic box by using the galaxy position and peculiar velocity. About 1,000 subboxes in the Illustris-TNG cosmological simulation are used to train the relation between DM density distribution and galaxy properties by using UNet-like convolutional neural network (CNN). The estimated DM density distributions have a good agreement with their truth values in terms of pixel-to-pixel correlation, the probability distribution of DM density, and matter power spectrum. We apply the trained CNN architecture to the galaxy properties from the Cosmicflows-3 catalogue to reconstruct the DM density distribution of the local universe. The reconstructed DM density distribution can be used to understand the evolution and fate of our local environment.

• Educational Technology International
• /
• v.20 no.2
• /
• pp.137-168
• /
• 2019

This study examined the effects of information volume and distribution on learners' cognitive load and recall in a mobile augmented reality (AR) environment. Information volume refers to the degree of information users are provided in a learning task, while information distribution indicates the way in which information is distributed, either in a virtual or real format. Sixteen undergraduate students participated in the study, which employed a 2 × 3 randomized block factorial design with repeated measures. Information volume and distribution were independent variables, and factors in learners' cognitive load (mental effort, perceived ease of use, and perceived task difficulty) and recall test scores were the dependent variables. Information volume had significant main effects on perceived ease of use and task difficulty, and recall test scores, while information distribution had significant main effects on perceived task difficulty and test scores. A detailed discussion and implications are provided.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1994.06c
• /
• pp.407-410
• /
• 1994

In this paper, we describe the new unsuperivised learning algorithm, SASOM. It can solve the defects of the conventional SOM that the state of network can't converge to the minimum point. The proposed algorithm uses the object function which can evaluate the state of network in learning and adjusts the learning rate flexibly according to the evaluation of the object function. We implement the simulated annealing which is applied to the conventional network using the object function and the learning rate. Finally, the proposed algorithm can make the state of network converged to the global minimum. Using the two-dimensional input vectors with uniform distribution, we graphically compared the ordering ability of SOM with that of SASOM. We carried out the recognitioin on the new algorithm for all Korean phonemes and some continuous speech.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.16 no.4
• /
• pp.270-275
• /
• 2016

We present an approach for acceleration actor-critic algorithm for reinforcement learning with continuous action space. Actor-critic algorithm has already proved its robustness to the infinitely large action spaces in various high dimensional environments. Despite that success, the main problem of the actor-critic algorithm remains the same-speed of convergence to the optimal policy. In high dimensional state and action space, a searching for the correct action in each state takes enormously long time. Therefore, in this paper we suggest a search accelerating function that allows to leverage speed of algorithm convergence and reach optimal policy faster. In our method, we assume that actions may have their own distribution of preference, that independent on the state. Since in the beginning of learning agent act randomly in the environment, it would be more efficient if actions were taken according to the some heuristic function. We demonstrate that heuristically-accelerated actor-critic algorithm learns optimal policy faster, using Educational Process Mining dataset with records of students' course learning process and their grades.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.16 no.2
• /
• pp.111-118
• /
• 2016

Artificial intelligence (AI) is making computer systems intelligent to do right thing. The AI is used today in a variety of fields, such as journalism, medical, industry as well as entertainment. The impact of AI is becoming larger day after day. In general, the AI system has to lead the optimal decision under uncertainty. But it is difficult for the AI system can derive the best conclusion. In addition, we have a trouble to represent the intelligent capacity of AI in numeric values. Statistics has the ability to quantify the uncertainty by two approaches of frequentist and Bayesian. So in this paper, we propose a methodology of the connection between statistics and AI efficiently. We compute a fixed value for estimating the population parameter using the frequentist learning. Also we find a probability distribution to estimate the parameter of conceptual population using Bayesian learning. To show how our proposed research could be applied to practical domain, we collect the patent big data related to Apple company, and we make the AI more intelligent to understand Apple's technology.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.1173-1176
• /
• 1996

Multilayer feedforward networks may be applied to identify the deterministic relationship between input and output data. When the results from the network require a high level of assurance, considering of the stochastic relationship between the data may be very important. The variance is one of the useful parameters to represent the stochastic relationship. This paper presents a new algorithm for a multilayer feedforward network to learn the variance of dispersed data without preliminary calculation of variance. In this paper, the network with this learning algorithm is named as a variance learning neural network(VALEAN). Computer simulation examples are utilized for the demonstration and the evaluation of VALEAN.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.385-398
• /
• 2021

The complexity of deep learning models affects the real-time performance of gesture recognition, thereby limiting the application of gesture recognition algorithms in actual scenarios. Hence, a residual learning neural network based on a deep convolutional neural network is proposed. First, small convolution kernels are used to extract the local details of gesture images. Subsequently, a shallow residual structure is built to share weights, thereby avoiding gradient disappearance or gradient explosion as the network layer deepens; consequently, the difficulty of model optimisation is simplified. Additional convolutional neural networks are used to accelerate the refinement of deep abstract features based on the spatial importance of the gesture feature distribution. Finally, a fully connected cascade softmax classifier is used to complete the gesture recognition. Compared with the dense connection multiplexing feature information network, the proposed algorithm is optimised in feature multiplexing to avoid performance fluctuations caused by feature redundancy. Experimental results from the ISOGD gesture dataset and Gesture dataset prove that the proposed algorithm affords a fast convergence speed and high accuracy.

• Journal of the Korean Society for Precision Engineering
• /
• v.14 no.6
• /
• pp.121-127
• /
• 1997

Multilayer feedforward networks may be applied to identify the deterministic relationship between input and output data. When the results from the network require a high level of assurance, consideration of the stochastic relationship between the input and output data may be very important. Variance is one of the effective parameters to deal with the stochastic relationship. This paper presents a new algroithm for a multilayer feedforward network to learn the variance of dispersed data without preliminary calculation of variance. In this paper, the network with this learning algorithm is named as a variance learning neural network(VALEAN). Computer simulation examples are utilized for the demonstration and the evaluation of VALEAN.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.272-275
• /
• 2022

The federated learning can be utilized in conjunction with the blockchain technology to provide good privacy protection and reward distribution mechanism in the field of intelligent IOT in edge computing scenarios. Nonetheless, the synchronous federated learning ignores the waiting delay due to the heterogeneity of edge devices (different computing power, communication bandwidth, and dataset size). Moreover, the potential of smart contracts was not fully explored to do some flexible design. This paper investigates the fusion application based on the FLchain, which is the combination of asynchronous federated learning and blockchain, discusses the communication optimization, and explores the feasible design of smart contract to solve some problems.

• International Journal of Computer Science & Network Security
• /
• v.24 no.5
• /
• pp.89-94
• /
• 2024

The main purpose of the study is to determine the main elements of the use of digital technologies for learning a foreign language in educational institutions. The era of digital technologies is a transition from the traditional format of working with information to a digital format. This is the era of the total domination of digital technologies. Digital technologies have gained an unprecedented rapid and general distribution. In recent years, all spheres of human life have already undergone the intervention of digital technologies. Therefore, it is precisely the educational industry that faces a difficult task - to move to a new level of education, where digital technologies will be actively used, allowing you to conveniently and quickly work in the information field for more effective learning and development. The study has limitations and they relate to the fact that the practical activities of the process of using digital technologies in the system of preparing the study of a foreign language were not taken into account.