다중혈관 관상동맥 환자에서 y-문합을 이용하여 양쪽 내흉동맥만을 사용한 우회술의 조기 성적

Domain-specific hardware is becoming a promising topic in the backdrop of improvement slow down for general-purpose processors due to the foreseeable end of Moore’s Law. Machine learning, especially deep neural networks (DNNs), has become the most dazzling domain witnessing successful applications in a wide spectrum of artificial intelligence (AI) tasks. The incomparable accuracy of DNNs is achieved by paying the cost of hungry memory consumption and high computational complexity, which greatly impedes their deployment in embedded systems. Therefore, the DNN compression concept was naturally proposed and widely used for memory saving and compute acceleration. In the past few years, a tremendous number of compression techniques have sprung up to pursue a satisfactory tradeoff between processing efficiency and application accuracy. Recently, this wave has spread to the design of neural network accelerators for gaining extremely high performance. However, the amount of related works is incredibly huge and the reported approaches are quite divergent. This research chaos motivates us to provide a comprehensive survey on the recent advances toward the goal of efficient compression and execution of DNNs without significantly compromising accuracy, involving both the high-level algorithms and their applications in hardware design. In this article, we review the mainstream compression approaches such as compact model, tensor decomposition, data quantization, and network sparsification. We explain their compression principles, evaluation metrics, sensitivity analysis, and joint-way use. Then, we answer the question of how to leverage these methods in the design of neural network accelerators and present the state-of-the-art hardware architectures. In the end, we discuss several existing issues such as fair comparison, testing workloads, automatic compression, influence on security, and framework/hardware-level support, and give promising topics in this field and the possible challenges as well. This article attempts to enable readers to quickly build up a big picture of neural network compression and acceleration, clearly evaluate various methods, and confidently get started in the right way.

Model Compression and Hardware Acceleration for Neural Networks: A Comprehensive Survey

Presently, educational institutions compile and store huge volumes of data, such as student enrolment and attendance records, as well as their examination results. Mining such data yields stimulating information that serves its handlers well. Rapid growth in educational data points to the fact that distilling massive amounts of data requires a more sophisticated set of algorithms. This issue led to the emergence of the field of educational data mining (EDM). Traditional data mining algorithms cannot be directly applied to educational problems, as they may have a specific objective and function. This implies that a preprocessing algorithm has to be enforced first and only then some specific data mining methods can be applied to the problems. One such preprocessing algorithm in EDM is clustering. Many studies on EDM have focused on the application of various data mining algorithms to educational attributes. Therefore, this paper provides over three decades long (1983–2016) systematic literature review on clustering algorithm and its applicability and usability in the context of EDM. Future insights are outlined based on the literature reviewed, and avenues for further research are identified.

A Systematic Review on Educational Data Mining

Educational data mining: Predictive analysis of academic performance of public school students in the capital of Brazil

An overview of MULTIMOORA for multi-criteria decision-making: Theory, developments, applications, and challenges

Main objective of this paper is to introduce the co ncept of similarity measures between two neutrosophic soft sets based on set the oretic approach and based on distance between two neutrosophic soft sets and to study som e basic properties. A decision making method is established based on similarity me asure between two neutrosophic sets. A decision making method is developed based on similarity measure between two neutrosophic soft sets and lastly an example is giv en to illustrate the proposed decision making method in a medical diagnosis problem.

Several Similarity Measures of Neutrosophic Soft Sets and its Application in Real Life Problems

Similarity measure is an important topic in fuzzy set theory (L. A. Zadeh, 1965). Similarity measure of fuzzy sets is now being extensively applied in many research fields such as fuzzy clustering, image processing, fuzzy reasoning, fuzzy neural network, pattern recognition, medical diagnosis, game theory, coding theory and several problems that contain uncertainties. The aim of this paper is to introduce the concept of similarity measure for interval-valued intuitionistic fuzzy soft sets based on set theoretic approach, some examples and basic properties are also studied. Lastly an application in a medical diagnosis problem is illustrated.

https://www.ntmsci.com/AjaxTool/GetArticleByPublishedArticleId?PublishedArticleId=38

Similarity measures for interval-valued intuitionistic fuzzy soft sets and its application in medical diagnosis problem

Singular value Decomposition applied to Associative Memory of Hopfield Neural Network

ST-DBSCAN is an extension of the traditional density based clustering algorithm DBSCAN. This algorithm is proposed for clustering spatio-temporal datasets. Spatio-temporal data refers to data which is stored as temporal slices of the spatial dataset. Here the spatial part of data identifies the location in data space and the temporal part of data represents the state in time. ST-DBSCAN can cluster data based on their spatial and temporal attributes and assigns data points to different clusters. ST-DBSCAN finds the clusters as crisp set. Since the crisp sets have a well-defined boundary, it becomes very difficult to find the accurate clusters. Our proposed algorithm, Rough-ST-DBSCAN, clusters data points as Rough Sets. Rough Sets are formal approximations of Crisp Sets in terms of a pair of sets which give the lower and the upper approximation of the original set. The lower approximation will be represented by a cluster that will contain the data points that must belong to the cluster and the upper approximation will be represented by a cluster boundary that will contain the data points that may belong to the cluster. So this proposed Rough-ST-DBSCAN algorithm can cluster data points based on their spatial and temporal density and also can determine the type of belongingness to a specific cluster.

A density-based clustering algorithm and experiments on student dataset with noises using Rough set theory

Smarandache in 1995 introduced the concept of neutrosophic set and in 2013 Maji introduced the notion of neutrosophic soft set, which is a hybridization of neutrosophic set and soft set.

/pdf/a-new-method-of-measuring-similarity-between-two-4woit20k8t.pdf

Anjan Mukherjee

Papers

Several Similarity Measures of Neutrosophic Soft Sets and its Application in Real Life Problems

Similarity measures for interval-valued intuitionistic fuzzy soft sets and its application in medical diagnosis problem

Singular value Decomposition applied to Associative Memory of Hopfield Neural Network

A density-based clustering algorithm and experiments on student dataset with noises using Rough set theory

A New Method of Measuring Similarity Between Two Neutrosophic Soft Sets and Its Application in Pattern Recognition Problems