안성수 교수

Recent discoveries on neural network pruning reveal that, with a carefully chosen layerwise sparsity, a simple magnitude-based pruning achieves state-of-the-art tradeoff between sparsity and performance. However, without a clear consensus on "how to choose," the layerwise sparsities are mostly selected algorithm-by-algorithm, often resorting to handcrafted heuristics or an extensive hyperparameter search. To fill this gap, we propose a novel importance score for global pruning, coined layer-adap

Abstract This paper discusses an adaptive procedure of a simplified power method for computing the eigenvector corresponding to the largest eigenvalue of an autocovariance matrix. The objective is to generate a suboptimal weight vector for an adaptive array operating in a multipath fading CDMA (code‐division multiple access) channel. The total computational load of the proposed procedure is about O (4 N ), including an autocovariance matrix update, where N is the number of weights. The performan

Markov Chain Monte Carlo (MCMC) and Belief Propagation (BP) are the most popular algorithms for computational inference in Graphical Models (GM). In principle, MCMC is an exact probabilistic method which, however, often suffers from exponentially slow mixing. In contrast, BP is a deterministic method, which is typically fast, empirically very successful, however in general lacking control of accuracy over loopy graphs. In this paper, we introduce MCMC algorithms correcting the approximation erro

We study the Maximum Weight Matching (MWM) problem for general graphs through the max-product Belief Propagation (BP) and related Linear Programming (LP). The BP approach provides distributed heuristics for finding the Maximum A Posteriori (MAP) assignment in a joint probability distribution represented by a Graphical Model (GM) and respective LPs can be considered as continuous relaxations of the discrete MAP problem. It was recently shown that a BP algorithm converges to the correct MWM assign

Designing efficient algorithms for combinatorial optimization appears ubiquitously in various scientific fields. Recently, deep reinforcement learning (DRL) frameworks have gained considerable attention as a new approach: they can automate the design of a solver while relying less on sophisticated domain knowledge of the target problem. However, the existing DRL solvers determine the solution using a number of stages proportional to the number of elements in the solution, which severely limits t

Computing the partition function $Z$ of a discrete graphical model is a fundamental inference challenge. Since this is computationally intractable, variational approximations are often used in practice. Recently, so-called gauge transformations were used to improve variational lower bounds on $Z$. In this paper, we propose a new gauge-variational approach, termed WMBE-G, which combines gauge transformations with the weighted mini-bucket elimination (WMBE) method. WMBE-G can provide both upper an

We study the maximum weight matching (MWM) problem for general graphs through the max-product belief propagation (BP) and related Linear Programming (LP). The BP approach provides distributed heuristics for finding the maximum a posteriori (MAP) assignment in a joint probability distribution represented by a graphical model (GM), and respective LPs can be considered as continuous relaxations of the discrete MAP problem. It was recently shown that a BP algorithm converges to the correct MAP/MWM a

Max-product Belief Propagation (BP) is a popular message-passing algorithm for computing a Maximum-A-Posteriori (MAP) assignment over a distribution represented by a Graphical Model (GM). It has been shown that BP can solve a number of combinatorial optimization problems including minimum weight matching, shortest path, network flow and vertex cover under the following common assumption: the respective Linear Programming (LP) relaxation is tight, i.e., no integrality gap is present. However, whe

This paper proposes a new blind adaptive algorithm for computing the weight vector of an antenna array system that provides the beam pattern having its maximum gain along the direction of the mobile target signal source in the presence of strong interference. The proposed algorithm provides a suboptimal weight vector maximizing the SINR (signal to interference plus noise ratio) with a linear computational load. Based on the analysis obtained from various simulations, it is observed that the prop

Markov Chain Monte Carlo (MCMC) and Belief Propagation (BP) are the most popular algorithms for computational inference in Graphical Models (GM). In principle, MCMC is an exact probabilistic method which, however, often suffers from exponentially slow mixing. In contrast, BP is a deterministic method, which is typically fast, empirically very successful, however in general lacking control of accuracy over loopy graphs. In this paper, we introduce MCMC algorithms correcting the approximation erro

In order to achieve the maximum gain along the desired signal, This work propose a beamforming algorithm that utilizes the generalized on-off algorithm. Also, we present a novel demodulation method enhancing the performance of the smart antenna by using the pilot channel of the CDMA2000 1X channel to obtain the exact weight vector.

Computing the partition function $Z$ of a discrete graphical model is a fundamental inference challenge. Since this is computationally intractable, variational approximations are often used in practice. Recently, so-called gauge transformations were used to improve variational lower bounds on $Z$. In this paper, we propose a new gauge-variational approach, termed WMBE-G, which combines gauge transformations with the weighted mini-bucket elimination (WMBE) method. WMBE-G can provide both upper an

연구목적 본 연구는 몽골 울란바토르시 소방공무원의 직무만족에 미치는 영향요인을 분석하여 직무만족을 제고할 수 있는 방안을 모색하고자 한다. 연구방법 조사대상자로는 몽골 울란바토르시 소방공무원 320명을 선정하였다. 독립변수로는 직무스트레스 요인, 인간관계 요인, 조직문화 요인, 직무보상 요인을 설정하였고, 직무만족 요인을 종속변수로 설정하였다. 통계프로그램인 SPSS 25.0을 사용하여 탐색적 요인분석, 신뢰도 분석, 위계적 회귀분석을 실시하였다. 결과 몽골 울란바토르시 소방공무원의 경우 독립변수인 직무부담, 역할갈등, 동료와의 관계, 발전문화, 집단문화, 승진, 보상은 직무만족에 영향을 미치는 것으로 분석되었다. 인구사회학적 변수 중 결혼상태, 근무부서(소방운전), 소득이 직무만족에 영향을 미치는 것으로 나타났다. 소방공무원의 결혼상태가 직무만족에 영향을 미친다는 분석결과는 선행연구와는 다른 결과라 할 수 있다. 결론 몽골 소방공무원의 직무만족을 제고하기 위해서는 첫째, 개인적 특