检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Tarasyuk, Igor V. A.P. Ershov Institute of Informatics Systems Siberian Branch of the Russian Academy of Sciences Acad. Lavrentiev pr. 6 Novosibirsk630090 Russia

We propose an extension with deterministically timed multiactions of discrete time stochastic and immediate Petri box calculus (dtsiPBC), previously presented by I.V. Tarasyuk, H. Macià and V. Valero. In dtsdPBC, non-negative integers specify multiactions with fixed (including zero) time delays. The step operational semantics is constructed via labeled probabilistic transition systems. The denotational semantics is defined on the basis of a subclass of labeled discrete time stochastic Petri nets with deterministic transitions. The consistency of both semantics is demonstrated. In order to evaluate performance, the corresponding semi-Markov chains and (reduced) discrete time Markov chains are analyzed.60J10, 60J20, 60K15, 68Q55, 68Q60, 68Q85 Copyright © 2019, The Authors. All rights reserved.

关键词： computer programming languages

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study on the Classification of Chinese News Articles by Machine Learning and Deep Learning Techniques

An Empirical Study on the Classification of Chinese News Art...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Chuen-Min Huang Yi-Jun Jiang National Yunlin University of Science and Technology Taiwan R.O.C.

ISBN: (纸本)9781728128177

This study compares Chinese news classification results of machine learning (ML) and deep learning (DL). In processing ML, we chose Support Vector Machine (SVM) and Naive Bayes (NB) to form three models: Word2Vec-SVM, TFIDF-SVM, and TFIDF-NB. Since NB assumes that the words are independent, this is different from the concept of related word distribution in Word2Vec, so the combination with NB is excluded. In processing DL, we adopted Bidirectional Long Short-Term Memory (Bi-LSTM), Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN), and used Word2Vec for word embedding. Experimental results showed that with proper word preprocessing, the difference of classification accuracy of ML and DL models is actually very small. Although the results show that Bi-LSTM performs the most accurate and has the lowest Loss compared to other DL techniques, its implementation process is the most time consuming. This study affirms the excellent results of CNN, while its Loss is the highest of the DL models. We also found that Word2Vec-SVM was superior to TFIDF-SVM in terms of efficiency, but its accuracy is not as good as expected. To summarize the classification accuracy in Bi-LSTM, LSTM, CNN, Word2vec-SVM, TFIDF-SVM, and NB are 89.3%, 88%, and 87.54%, 85.32%, 87.35%, 86.56%, respectively.

关键词： Machine learning Deep learning TFIDF Word2Vec News classification Machine Learning Taxonomy Word computer programming languages Artificial Intelligence niobium empirical studies Learning Short-Term Memory

来源：评论

学校读者我要写书评

暂无评论

Utilization of Metadata and Data Models to Enhance Machine Learning

Utilization of Metadata and Data Models to Enhance Machine L...

引用

International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)

作者： Manoj Gorai Manisha J. Nene Department of Computer Science and Engineering Defence Institute of Advanced Technology Pune Maharashtra INDIA

ISBN: (纸本)9781728148274

Data plays the most significant role to attain efficiency in performing a task using Machine Learning (ML) techniques. Metadata (MD) represents data of data. MD extraction and data attribute selection play a vital role in defining the performance of ML models. The study in this paper focuses on the role of MD, data attributes and data models that define the learning capability of ML to evolve with human-like capability to learn and draw inferences. To evolve with such artificially intelligent autonomous systems, the study in this paper is a preliminary step towards applying ML techniques on textual data for performing syntactic analysis, further to evolve with semantic and behavioral analysis. Based on the rigorous survey study and observations, this paper concludes with the description of the parameters to quantify the performance of ML model which are essential to define the performance characteristics of ML. The increased deployment of ML is observed in the recent Artificial Intelligence arena, and hence the study contributes towards evolving performance parameters in applications that employ ML techniquestextbf.

关键词： Machine learning Metadata Data model Metadata computer programming languages data models Artificial Intelligence Machine Learning performance characteristics assessment of behavior

来源：评论

学校读者我要写书评

暂无评论

System Model for Syntax Free Coding

System Model for Syntax Free Coding

引用

Global Conference for Advancement in Technology (GCAT)

作者： Pratul Trivedi Pranav Kajgaonkar Abhishek Kulkarni Nikhil Kolte Bhavana Kanawade Department of Information Technology International Institute of Information Technology Savitiribai Phule Pune University MH India

ISBN: (纸本)9781728136950

Every programming language has its own attributes, advantages and its own syntax. The logical reasoning applied by the programmer also requires awareness of the syntax specific to that language. Writing correct code depends heavily on syntax proficiency. Perhaps this can be asserted as an impediment of general programming languages. The new learners of a particular programming language find it difficult to cope up with the syntax requirement of that particular language. This not only increases the time required to learn a language but also shifts the focus of the user from logical reasoning. In order to shun the tedious approach of learning the syntax of a language, the approach of converting the user's logic drafted in natural language directly into the appropriate programming syntax can be used. This approach will not only grant the user the ability to use natural language but will eliminate the syntax dependency as well. Since logic construction for a solution to a problem is constrained by the syntax of a programming language, we propose a system that allows the user to provide a simple English statement as input to the system, which will then be translated into syntactically correct *** show that the system works efficiently with more than 80% accuracy. With each iteration, the dataset gets trained and updated, further increasing the precision and recall of the system. We also convey that, with the help of this system the syntax dependency can be eliminated, thereby increasing the user's efficiency.

关键词： computational linguistics learning (artificial intelligence) syntax COMPUTATIONAL LINGUISTICS Language computer programming languages Systems modelling Consumers computer personnel CORRECTING CODE

来源：评论

学校读者我要写书评

暂无评论

Neural networks for modeling source code edits

arXiv

引用

arXiv 2019年

作者： Zhao, Rui Bieber, David Swersky, Kevin Tarlow, Daniel Google Brain

programming languages are emerging as a challenging and interesting domain for machine learning. A core task, which has received significant attention in recent years, is building generative models of source code. However, to our knowledge, previous generative models have always been framed in terms of generating static snapshots of code. In this work, we instead treat source code as a dynamic object and tackle the problem of modeling the edits that software developers make to source code files. This requires extracting intent from previous edits and leveraging it to generate subsequent edits. We develop several neural networks and use synthetic data to test their ability to learn challenging edit patterns that require strong generalization. We then collect and train our models on a large-scale dataset of Google source code, consisting of millions of fine-grained edits from thousands of Python developers. From the modeling perspective, our main conclusion is that a new composition of attentional and pointer network components provides the best overall performance and scalability. From the application perspective, our results provide preliminary evidence of the feasibility of developing tools that learn to predict future edits. Copyright © 2019, The Authors. All rights reserved.

关键词： computer programming languages

来源：评论

学校读者我要写书评

暂无评论

Comparing the Effects of Annotation Type on Machine Learning Detection Performance

Comparing the Effects of Annotation Type on Machine Learning...

引用

IEEE/CVF Conference on computer Vision and Pattern Recognition Workshops

作者： James F. Mullen Franklin R. Tanner Phil A. Sallee Raytheon Corporation

ISBN: (数字)9781728125060

ISBN: (纸本)9781728125077

The most prominent machine learning (ML) methods in use today are supervised, meaning they require ground-truth labeling of the data on which they are trained. Annotating data is arduous and expensive. Additionally, data sets for image object detection may be annotated by drawing polygons, drawing bounding boxes, or providing single points on targets. Selection of annotation technique is a tradeoff between time to annotate and accuracy of the annotation. When annotating a dataset for machine object recognition algorithms, researchers may not know the most advantageous method of annotation for their experiments. This paper evaluates the performance tradeoffs of three alternative methods of annotating imagery for use in ML. A neural network was trained using the different types of annotations and compares the detection accuracy of and differences between the resultant models. In addition to the accuracy, cost is analyzed for each of the models and respective datasets.

关键词： ANNOTATIONS Dataset tradeoffs bounding boxes Artificial Intelligence Machine Learning alternative methods computer programming languages drawing Drawing

来源：评论

学校读者我要写书评

暂无评论

Machine Learning based Energy Efficient Wireless Sensor Network

Machine Learning based Energy Efficient Wireless Sensor Netw...

引用

International Conference on Power Electronics, Control and Automation (ICPECA)

作者： Sonam Lata Shabana Mehfuz Dept. of Electrical Engineering Jamia Millia Islamia Delhi India

ISBN: (纸本)9781728139593

In case of no fixed infrastructure (military applications and emergency rescue operations) and we need to build a network with low cost, Wireless sensor networks (WSNs) are useful. We have no fixed routing protocol, or intrusion detection technique available for them because WSNs are dynamic in nature and individual nodes of the network are required for this to be done. Nodes are mobile in most of the applications of WSNs, so they depend on battery power and availability of limited resources which shows that power consumption is an effective research area for performing a set of tasks in WSNs. To deal with such an issue, machine learning (ML) techniques (self-learning algorithms, working without programming or human intervention) can be applied effectively according to the application requirement. In this paper, we have done comparative about several ML-based techniques for WSNs. In addition, we also analyzed ML techniques for clustering and energy harvesting. At the end, we present a summary of ML techniques for both clustering and energy harvesting with some open issues.

关键词： Wireless sensor network Network-Lifetime Machine learning Energy efficiency Clustering Wireless sensor networks Energy efficiency Artificial Intelligence Machine Learning Cluster Analysis energy harvesting computer programming languages Battery power supply Ganglia

来源：评论

学校读者我要写书评

暂无评论

Summarizing Source Code with Transferred API Knowledge 27

Summarizing Source Code with Transferred API Knowledge

引用

27th International Joint Conference on Artificial Intelligence (IJCAI)

作者： Hu, Xing Li, Ge Xia, Xin Lo, David Lu, Shuai Jin, Zhi Peking Univ Key Lab High Confidence Software Technol Minist Educ Beijing Peoples R China Peking Univ Inst Software EECS Beijing Peoples R China Monash Univ Fac Informat Technol Clayton Vic Australia Singapore Management Univ Sch Informat Syst Singapore Singapore

ISBN: (纸本)9780999241127

Code summarization, aiming to generate succinct natural language description of source code, is extremely useful for code search and code comprehension. It has played an important role in software maintenance and evolution. Previous approaches generate summaries by retrieving summaries from similar code snippets. However, these approaches heavily rely on whether similar code snippets can be retrieved, how similar the snippets are, and fail to capture the API knowledge in the source code, which carries vital information about the functionality of the source code. In this paper, we propose a novel approach, named TL-CodeSum, which successfully uses API knowledge learned in a different but related task to code summarization. Experiments on large-scale real-world industry Java projects indicate that our approach is effective and outperforms the state-of-the-art in code summarization.

关键词： computer programming languages

来源：评论

学校读者我要写书评

暂无评论

A Novel Chaos Theory Inspired Neuronal Architecture

A Novel Chaos Theory Inspired Neuronal Architecture

引用

Global Conference for Advancement in Technology (GCAT)

作者： N B Harikrishnan Nithin Nagaraj Consciousness Studies Programme National Institute of Advanced Studies Bengaluru India

ISBN: (纸本)9781728136950

The practical success of widely used machine learning (ML) and deep learning (DL) algorithms in Artificial Intelligence (AI) community owes to availability of large datasets for training and huge computational resources. Despite the enormous practical success of AI, these algorithms are only loosely inspired from the biological brain and do not mimic any of the fundamental properties of neurons in the brain, one such property being the chaotic firing of biological neurons. This motivates us to develop a novel neuronal architecture where the individual neurons are intrinsically chaotic in nature. By making use of the topological transitivity property of chaos, our neuronal network is able to perform classification tasks with very less number of training samples. For the MNIST dataset, with as low as 0.1% of the total training data, our method outperforms ML and matches DL in classification accuracy for up to 7 training samples/class. For the Iris dataset, our accuracy is comparable with ML algorithms, and even with just two training samples/class, we report an accuracy as high as 95.8%. This work highlights the effectiveness of chaos and its properties for learning and paves the way for chaos-inspired neuronal architectures by closely mimicking the chaotic nature of neurons in the brain.

关键词： chaos learning (artificial intelligence) neural nets pattern classification topology chaos Neural network Pattern recognition Chaos theory topology Artificial Intelligence Neurons Training ARCHITECTURE computer programming languages Respiratory Inspiration Cerebrum Dataset

来源：评论

学校读者我要写书评

暂无评论

ICT and Mobile Technology Features Predicting the University of Indian and Hungarian Student for the Real-Time

ICT and Mobile Technology Features Predicting the University...

引用

International Conference on System Modeling & Advancement in Research Trends (SMART)

作者： Chaman Verma Veronika Stoffová Zoltán Illés Mandeep Singh Eötvös Loránd University Budapest Hungary Trnava University Trnava Slovakia Chandigarh University Chandigarh India

ISBN: (数字)9781728132457

ISBN: (纸本)9781728132464

Feature extraction has a vibrant part in Machine learning (ML) to identify the data patterns with optimum accuracy. We proposed some significant features to predict the student's institution or university based on their answers in the technological survey. Four experiments were performed in IBM SPSS Modeler version 18.2 using 4 ML to resolve the binary classification problem. In the university prediction problem., the uppermost accuracy of 94.26% is provided by eXtreme Gradient Boosting Tree (XGBT) and suggested 18 significant features out of a total of 37. Further., the Artificial Neural Network (ANN) with boosting scored second maximum accuracy of 93.96% and recommended 10 significant features; Support Vector Machine (SVM) provided third-highest accuracy of 92.45% with the recommendation of 12 features; and Random Tree (RT) attained the least accuracy 92.15% with recommendation of 10 important features. The findings of the paper conclude that the XGBT classifier outperformed others in prediction. Also., a noteworthy dissimilarity was found between XGBT's accuracy and SVM's accuracy., RT's accuracy.

关键词： Supervisor Machine learning Predicator importance University prediction Performance Evaluation Performance Evaluation universities information technology Information and communication technology International Criminal Tribunal Mobile Technologies Data analysis Students Feature extraction Indians Artificial neural networks Hungarian Support Vector Network computer programming languages

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：