• KIPS Transactions on Computer and Communication Systems
• /
• v.6 no.7
• /
• pp.315-320
• /
• 2017

In this paper, I design a new scheme that is immune to malicious attack based on the weighted voting game. By using stochastic learning, the proposed scheme can revoke the certification of malicious node. Through the revocation process, the proposed scheme can effectively adapt the dynamic Mobile Ad hoc network situation. Simulation results clearly indicate that the developed scheme has better performance than other existing schemes under widely diverse network environments.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.12
• /
• pp.5820-5834
• /
• 2017

This paper investigates the channel selection problem with dynamic users and the asymmetric interference relation in distributed opportunistic spectrum access systems. Since users transmitting data are based on their traffic demands, they dynamically compete for the channel occupation. Moreover, the heterogeneous interference range leads to asymmetric interference relation. The dynamic users and asymmetric interference relation bring about new challenges such as dynamic random systems and poor fairness. In this article, we will focus on maximizing the tradeoff between the achievable utility and access cost of each user, formulate the channel selection problem as a directional graphical game and prove it as an exact potential game presenting at least one pure Nash equilibrium point. We show that the best NE point maximizes both the personal and system utility, and employ the stochastic learning approach algorithm for achieving the best NE point. Simulation results show that the algorithm converges, presents near-optimal performance and good fairness, and the directional graphical model improves the systems throughput performance in different asymmetric level systems.

• Journal of the Korean Society for Precision Engineering
• /
• v.14 no.10
• /
• pp.141-150
• /
• 1997

분산은 확률모델을 표현하는 유용한 변수중 하나이다. 입력변수에 대한 함수로 표현되는 조건부 분산을 학습하는 신경회로망에 대한 많은 연구가 있어왔다. VALEAN이라는 신경회로망 역시 이러한 많은 연구중 하나인데 이것은 기본적으로 feedforward 다층 퍼셉트론 구조를 가지며 새롭게 제시된 에너지 함수를 사용하고 있다. 이 논문에서는 이 에너지 모델에 의해 결정되는 피드백에러(델타)가 신경망의 transient, steady state에서 미치는 영향을 다루었다. 과도 상태 분석에서는 델타와 수렴성, 안정성에 관한 내용을 다루고 모의 실험을 하였으며 정상 상태 분석에서는 신경회로망의 정상상태 에러의 크기와 델타의 크기사이의 상관관계에 대하여 다루었다. 학습 알고 리듬이 확률적이므로 정상상태 역시 확률적인 상태를 나타낸다. 따라서 델타의 크기에 따른 정상 상태 에러의 최대치는 확률적인 모델을 가지게 된다. 여기서는 이 확률 관계를 분석적으로 규명하고 이에 따라 원하는 신뢰도로 정상 상태 에러를 제어하기 위해 필요한 델타의 크기를 예측할 수 있는 이론적 배경을 마련하게 된다.

• Proceedings of the KIEE Conference
• /
• 1998.07g
• /
• pp.2296-2298
• /
• 1998

In this paper, an on-chip learning pulse-mode digital neural network with a massively parallel yet compact and flexible network architecture is suggested. Algebraic neural operations are replaced by stochastic processes using pseudo-random sequences and simple logic gates are used as basic computing elements. Using Back-propagation algorithm both feed-forward and learning phases are efficiently implemented with simple logical gates. RNG architecture using LFSR and barrel shifter are adopted to avoid some correlation between pulse trains. Suggested network is designed in digital circuit and its performance is verified by computer simulation.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.1
• /
• pp.107-114
• /
• 1994

Hardware implementation of the on-chip learning artificial neural networks is important for real-time processing. A pRAM model is based on probabilistic firing of a biological neuron and can be implemented in the VLSI circuit with learning capability. We derive a backpropagation learning algorithm for the pRAM networks and present its circuit implementation with stochastic computation. The simulation results confirm the good convergence of the learning algorithm for the pRAM networks.

• East Asian Economic Review
• /
• v.25 no.4
• /
• pp.403-424
• /
• 2021

AdaBoost tweaks the sample weight for each training set used in the iterative process, however, it is demonstrated that it provides more correlated errors as the boosting iteration proceeds if models' accuracy is high enough. Therefore, in this study, we propose a novel way to improve the performance of the existing AdaBoost algorithm by employing heterogeneous models and a stochastic twist. By employing the heterogeneous ensemble, it ensures different models that have a different initial assumption about the data are used to improve on diversity. Also, by using a stochastic algorithm with a decaying convergence rate, the model is designed to balance out the trade-off between model prediction performance and model convergence. The result showed that the stochastic algorithm with decaying convergence rate's did have a improving effect and outperformed other existing boosting techniques.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.4
• /
• pp.319-326
• /
• 2015

Recently in the fields o f stochastic optimal control ( SOC) and reinforcemnet l earning (RL), there have been a great deal of research efforts for the problem of finding data-based sub-optimal control policies. The conventional theory for finding optimal controllers via the value-function-based dynamic programming was established for solving the stochastic optimal control problems with solid theoretical background. However, they can be successfully applied only to extremely simple cases. Hence, the data-based modern approach, which tries to find sub-optimal solutions utilizing relevant data such as the state-transition and reward signals instead of rigorous mathematical analyses, is particularly attractive to practical applications. In this paper, we consider a couple of methods combining the modern SOC strategies and approximate inference together with machine-learning-based data treatment methods. Also, we apply the resultant methods to a variety of application domains including financial engineering, and observe their performance.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.101-101
• /
• 2020

Traditional stochastic simulation of hydroclimatological variables often underestimates the variability and correlation structure of larger timescale due to the difficulty in preserving long-term memory. However, the Long Short-Term Memory (LSTM) model illustrates a remarkable long-term memory from the recursive hidden and cell states. The current study, therefore, employed the LSTM model in stochastic generation of hydrologic and climate variables to examine how much the LSTM model can preserve the long-term memory and overcome the drawbacks of conventional time series models such as autoregressive (AR). A trigonometric function and the Rössler system as well as real case studies for hydrological and climatological variables were tested. Results presented that the LSTM model reproduced the variability and correlation structure of the larger timescale as well as the key statistics of the original time domain better than the AR and other traditional models. The hidden and cell states of the LSTM containing the long-memory and oscillation structure following the observations allows better performance compared to the other tested conventional models. This good representation of the long-term variability can be important in water manager since future water resources planning and management is highly related with this long-term variability.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.3
• /
• pp.647-654
• /
• 2023

Deep Learning is a useful method for classifying and recognizing complex data such as images and text, and the accuracy of the deep learning method is the basis for making artificial intelligence-based services on the Internet useful. However, the vast amount of user da vita used for training in deep learning has led to privacy violation problems, and it is worried that companies that have collected personal and sensitive data of users, such as photographs and voices, own the data indefinitely. Users cannot delete their data and cannot limit the purpose of use. For example, data owners such as medical institutions that want to apply deep learning technology to patients' medical records cannot share patient data because of privacy and confidentiality issues, making it difficult to benefit from deep learning technology. In this paper, we have designed a privacy preservation technique-applied deep learning technique that allows multiple workers to use a neural network model jointly, without sharing input datasets, in multi-party system. We proposed a method that can selectively share small subsets using an optimization algorithm based on modified stochastic gradient descent, confirming that it could facilitate training with increased learning accuracy while protecting private information.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.3
• /
• pp.633-640
• /
• 1999

Reinforcement learning performs learning through interacting with trial-and-error in dynamic environment. Therefore, in dynamic environment, reinforcement learning method like Q-learning and TD(Temporal Difference)-learning are faster in learning than the conventional stochastic learning method. However, because many of the proposed reinforcement learning algorithms are given the reinforcement value only when the learning agent has reached its goal state, most of the reinforcement algorithms converge to the optimal solution too slowly. In this paper, we present COMREL(COMpressed REinforcement Learning) algorithm for finding the shortest path fast in a maze environment, select the candidate states that can guide the shortest path in compressed maze environment, and learn only the candidate states to find the shortest path. After comparing COMREL algorithm with the already existing Q-learning and Priortized Sweeping algorithm, we could see that the learning time shortened very much.