检索结果-内蒙古大学图书馆

A practical algorithm for learning disjunctive abstraction heuristics in static program analysis

INFORMATION AND SOFTWARE TECHNOLOGY 2021年 135卷 106564-106564页

作者： Jeon, Donghoon Jeon, Minseok Oh, Hakjoo Korea Univ Dept Comp Sci & Engn Seoul South Korea

Context: The precision and cost of static analysis are determined by abstraction heuristics (e.g., strategies for abstracting calling contexts, heap locations, etc.), but manually designing effective abstraction heuristics requires a huge amount of engineering effort and domain knowledge. Recently, data-driven static analysis has emerged to address this challenge by learning such heuristics automatically from a set of training programs. Objective: We present a practical algorithm for learning disjunctive abstraction heuristics in data-driven static analysis. We build on a recently proposed approach that can learn nontrivial program properties by disjunctive boolean functions. However, the existing approach is practically limited as it assumes that the most precise abstraction is cheap for the training programs;the algorithm is inapplicable if the most precise abstraction is not scalable. The objective of this paper is to mitigate this limitation. Method: Our algorithm overcomes the limitation with two new ideas. It systematically decomposes the learning problem into feasible subproblems, and it can search through the abstraction space from the coarse to fine-grained abstractions. With this approach, our algorithm is able to learn heuristics when static analysis with the most precise abstraction is not scalable over the training programs. Results: We show our approach is effective and generally applicable. We applied our approach to a context sensitive points-to analysis for Java and a flow-sensitive interval analysis for C. Experimental results show that our algorithm is efficient. For example, our algorithm can learn heuristics for 3-object-sensitive analysis for which the existing learning algorithm is too expensive to learn any useful heuristics. Conclusion: Our algorithm makes a state-of-the-art technique for data-driven static analysis more practical.

关键词： Data-driven static analysis learning algorithm

来源：评论

学校读者我要写书评

暂无评论

REINFORCEMENT learning CONTROL FOR SHIP STEERING USING RECURSIVE LEAST-SQUARES algorithm

引用

IFAC Proceedings Volumes 2005年第1期38卷 133-138页

作者： Zhi-peng Shen Chen Guo Shi-chun Yuan Lab of Simulation and Control of Navigation Systems Dalian Maritime Univ. Dalian 116026 China State Key Laboratory of Intelligent Technology and system Tsinghua University Beijing 100084 China

Recursive least-squares temporal difference algorithm (RLS-TD) is deduced, which can use data more efficiently with fast convergence and less computational burden. Reinforcement learning based on recursive least-squares methods is applied to ship steering control, as provides an efficient way for the improvement of ship steering control performance. It removes the defect that the conventional intelligent algorithm learning must be provided with some sample data. The parameters of controller are on-line learned and adjusted. Simulation results show that the ship course can be properly controlled in case of the disturbances of wave, wind, current. It is demonstrated that the proposed algorithm is a promising alternative to conventional autopilots.

关键词： Recursive squares methods learning algorithm Action network Ship control Simulation

来源：评论

学校读者我要写书评

暂无评论

A new enhanced learning approach to automatic image classification based on Salp Swarm algorithm

引用

COMPUTER SYSTEMS SCIENCE AND ENGINEERING 2019年第2期34卷 91-100页

作者： Nejad, Mohammad Behrouzian Shiri, Mohammad Ebrahim Islamic Azad Univ Borujerd Branch Dept Comp Engn Borujerd Iran Amirkabir Univ Dept Math & Comp Sci Tehran Iran

In this paper we propose a new image classification technique. According to this note that most research focuses on extraction of features in the frequency domain, location, and reduction of feature dimensions, in this research we focused on learning step in image classification. The main aim is to use the heuristic methods to increase the function of the estimator of the learning algorithm and continue to achieve the desired state, as well as categorization without user interference and automatically performed by the model produced from the above steps. So, in this paper, a new learning approach based on the Salp Swarm algorithm was proposed that was implemented and evaluated on learning algorithm Decision Tree, K-Nearest Neighbors and Naive Bayes. The results demonstrate the improvement of the performance of learning algorithms in all the achieved criteria by using the SSA algorithm in comparison with traditional learning algorithms. In the accuracy, sensitivity, classification error and F1 criterion, the best performance of the proposed model is using the Decision Tree learning method with values of 99.17%, 100%, 0.83% and 95.65% respectively. In the specificity and precision criterion, the best performance of the proposed model is based on K-Nearest Neighbors learning method with values of 100%.

关键词： Image Mining Image Classification learning algorithm Salp Swarm algorithm

来源：评论

学校读者我要写书评

暂无评论

DLF: A Deep learning Framework Using Convolution Neural Network algorithm for Breast Cancer Detection and Classification

引用

TRAITEMENT DU SIGNAL 2024年第3期41卷 1101-1114页

作者： Govindarajan, Kalpana Narayanasamy, Deepa Saveetha Inst Med & Tech Sci Saveetha Sch Engn Dept Comp Sci & Engn Chennai 602105 India

Breast cancer is one of the most frequently affecting second types of cancer in men and women worldwide. Of the overall types of cancer, 25% of them are breast cancer in women. Erratic development of breast cells results in breast cancer. The growth of cancer increases the metastasizing of the tissues, spreads fast to the other parts of the body, and results in death. The medical industry requires an efficient algorithm to detect and classify the severity level of breast cancers with the metastasis of the affected tissues. Several earlier research works have focused on constructing a computer algorithm to diagnose breast cancer images to detect and classify cancer. The earlier algorithms involved more sub -functions or procedures in completing individual tasks separately, thus increasing the computational and time complexity. This paper introduces a Deep learning Framework (DLF) to diagnose breast images automatically and speedily with less complexity. The proposed DLF includes a few image processing tasks to improve the quality of the input image and increase classification accuracy. Recently, Convolution Neural Network has been used as an extraordinary class of models for image recognition processes. CNN is one of the deep learning models that can extract the entire set of image features and use them for analysis and classification. Thus, this paper implements a deep CNN for diagnosing and classifying benign and malignant cancers from input datasets with Python coding-the deep form of the CNN obtained by increasing the number of hidden layers and epochs. The experiment proves that CNN is highly reliable compared to the existing algorithm.

关键词： breast cancer mammogram image feature extraction benign malignant CNN deep learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Machine learning algorithms for teaching AI chat bots

引用

Procedia Computer Science 2021年 190卷 735-744页

作者： Evgeny Tebenkov Igor Prokhorov National Research Nuclear University MEPhI (Moscow Engineering Physics Institute) Moscow Russia

Machine learning is a method of data analysis, which allows the analytical system to learn in the course of solving many similar problems. Machine learning is based on the idea that analytical systems can learn how to identify patterns and make decisions with minimal human involvement. The history of already completed dialogues between users is used to train chat bots for automated communication with interlocutors. There are many machine learning algorithms, and this article describes the most popular of them and their use for teaching chat bots.

关键词： Machine learning artificial intelligence chat bots algorithms of learning chat bots learning algorithm machine learning algorithm.

来源：评论

学校读者我要写书评

暂无评论

AN EFFECTIVE MODEL FOR CARBON DIOXIDE EMISSIONS PREDICTION: COMPARISON OF ARTIFICIAL NEURAL NETWORKS learning algorithmS

引用

INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE AND APPLICATIONS 2014年第3期13卷 1450014页

作者： Abdullah, Lazim Pauzi, Herrini Mohd Univ Malaysia Terengganu Sch Informat & Appl Math Kuala Terengganu 21030 Malaysia

This paper intends to compare various learning algorithms available for training the multi-layer perceptron (MLP) type of artificial neural networks (ANNs). By using different learning algorithms, this study investigates the performances of gradient descent (GD) algorithm;Levenberg-Marquardt (LM) algorithm;and also Boyden, Fletcher, Goldfarb and Shannon (BFGS) algorithm to predict the emissions of carbon dioxide (CO2) in Malaysia. The impact factors of emissions, such as energy use;gross domestic product per capita;population density;combustible renewable and waste;also CO2 intensity were employed in developing all ANN models investigated in this study. A wide variety of standard statistical performance evaluation measures were employed to evaluate the performances of various ANN models developed. The results obtained in this study indicate that the LM algorithm outperformed both BFGS and GD algorithms.

关键词： CO2 emissions forecasting artificial neural network learning algorithm

来源：评论

学校读者我要写书评

暂无评论

A learning method for energy optimization of the plug-in hybrid electric bus

引用

Science China(Technological Sciences) 2015年第7期58卷 1242-1249页

作者： SUN Yong CHEN Zheng YAN BingJie YOU SiXiong College of Information Science and Engineering Ocean University of China State Key Laboratory of Automotive Safe and Energy Tsinghua University School of Sciences Ningbo University of Technology

The optimal energy management for a plug-in hybrid electric bus(PHEB)running along the fixed city bus route is an important technique to improve the vehicles’fuel economy and reduce the bus *** the inherently high regularities of the fixed bus routes,the continuous state Markov decision process(MDP)is adopted to describe a cost function as total gas and electric consumption *** a learning algorithm is proposed to construct such a MDP model without knowing the all parameters of the ***,fitted value iteration algorithm is given to approximate the cost function,and linear regression is used in this fitted value *** results show that this approach is feasible in searching for the control strategy of *** this method has its own advantage comparing with the CDCS ***,a test based on a real PHEB was carried out to verify the applicable of the proposed method.

关键词： plug-in hybrid electric （PHEB） control strategy dynamic programming （DP） learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Performance comparison of artificial neural networks learning algorithms and activation functions in predicting severity of autism

引用

NETWORK MODELING AND ANALYSIS IN HEALTH INFORMATICS AND BIOINFORMATICS 2015年第1期4卷 2-2页

作者： Chand, Yamini Alam, Md Afroz Tejaswini, Y. R. S. N. Karunya Univ Sch Biotechnol & Hlth Sci Dept Bioinformat Coimbatore Tamil Nadu India Vasavi Med & Res Ctr Hyderabad Andhra Pradesh India

Artificial neural networks are one of the most efficient methods for pattern recognition and have a vast range of applications for aiding medical decision making. The proposed study applies feed-forward back-propagation neural networks as a classifier and compares the combination of nine learning algorithms and three activation functions to build a knowledge-based system with the best network architecture for predicting the severity of autism. The performances of the derived models were evaluated based on statistical criteria such as mean squared error (MSE), mean absolute percentage error (MAPE), root mean squared error (RMSE), regression (R value), training time and number of epochs. The study findings showed that the optimal performance was achieved by model MLP_LM_104 trained on Levenberg-Marquardt (LM) back-propagation algorithm having network topology of 40-10-4 with purelin and tansig activation functions in hidden and output layers. The regression coefficients for training, validation and test datasets were 0.996, 0.996 and 0.994, respectively. The MSE, RMSE and MAPE were 2.26 x 10(-4), 1.50 x 10(-2) and 1.13, respectively. Furthermore, BFGS quasi-Newton (BFG), conjugate gradient, gradient descent and resilient back-propagation (RP) algorithms did not perform well. Models trained with BFG algorithms required longer training time, whereas the performance of models trained on RP algorithm got worse as the numbers of hidden neurons were increased.

关键词： Artificial neural network learning algorithm Activation function Prediction Autism Knowledge-based system

来源：评论

学校读者我要写书评

暂无评论

GENERAL CONSIDERATION OF 4-LAYER SERIES-COUPLED MACHINES WITH learning MECHANISMS

引用

KYBERNETIK 1973年第2期13卷 95-103页

作者： SHIMURA, M GEORGE, FH Dept. of Cybernetics Brunel University Uxbridge Middlesex England

In general, four-layer series-coupled machines can be divided into two types according to learning methods. One is the machine in which the change of variable connecting coefficients depends upon the state of association units in both layers AI and AII. The other type is the machine in which the change depends upon the state of association units in only layer AI. In this paper, four-layer series-coupled machines of the latter type are discussed. They can be classified into six types according to the properties of the units and the learning algorithm. Some mathematical models of the machines are developed in which both excitory and inhibitory stimuli are used. The performance of these models compare favourably with machines in which only excitory stimuli are used. learning procedure in each machine is analyzed and the convergence conditions are derived. Furthermore, some applications of the fourlayer machines to multi-category classification are discussed.

关键词： Mathematical Model learning algorithm General Consideration Convergence Condition Learn Procedure

来源：评论

学校读者我要写书评

暂无评论

Fast and Effective learning for Fuzzy Cognitive Maps: A Method Based on Solving Constrained Convex Optimization Problems

引用

IEEE TRANSACTIONS ON FUZZY SYSTEMS 2020年第11期28卷 2958-2971页

作者： Lu, Wei Feng, Guoliang Liu, Xiaodong Pedrycz, Witold Zhang, Liyong Yang, Jianhua Dalian Univ Technol Sch Control Sci & Engn Dalian 116023 Peoples R China Northeast Elect Power Univ Sch Automat Engn Jilin 132012 Jilin Peoples R China Univ Alberta Dept Elect & Comp Engn Edmonton AB T6R 2V4 Canada Polish Acad Sci Syst Res Inst PL-00901 Warsaw Poland King Abdulaziz Univ Fac Engn Dept Elect & Comp Engn Jeddah 21589 Saudi Arabia

The learning of fuzzy cognitive maps (FCMs) is a timely issue pursued by numerous researchers. Many learning methods, such as population-based algorithms and some hybrid algorithms, have been developed and applied to many fields resulting in better performance. However, those learning algorithms also exhibit obvious limitations: some of them either are difficult to handle the learning problem of large-scale FCM or extremely time-consuming with high computational overload. Furthermore, the learning problem of FCM with noisy data is rarely considered in existing algorithms. In this article, a fast and efficient method for learning FCM is proposed. It first transforms the learning problem of the FCM into a convex optimization problem with constraints, and then, the classic interior-point methods are invoked to solve the optimization problem to obtain the optimized weight matrix of the FCM. A series of experiments involving synthetic data, noisy synthetic data, real data, and publicly available data with noise are considered to demonstrate that the proposed method can rapidly and efficiently learn small-scale and large-scale FCMs and deal with the problem of learning FCM from noisy historical data.

关键词： Convex optimization fuzzy cognitive maps (FCMs) learning algorithm

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：