is ar stu ed d vi y re aC s o ou urc rs e eH w er as o. co m COMSATS UNIVERSITY ISLAMABAD, ABBOTTABAD CAMPUS Object oriented softwaere engineering Assignment no# 4 DATE: 13 JUNE 2021 Topic of Assignment: sh Th Summary of research paper This study source was downloaded by 100000803991717 from CourseHero.com on 06-27-2021 23:34:51 GMT -05:00 https://www.coursehero.com/file/98473585/OOSE-ASSIGN-4docx/ TITLE: Studying Software Engineering Patterns for Designing Machine Learning Systems is ar stu ed d vi y re aC s o ou urc rs e eH w er as o. co m What is Machine learning: Machine learning is a method of data analysis that automates analytical model building. It is a branch of Artificial intelligence based on the idea that systems can learn from data, identify patterns and make decisions with minimal human intervention. Why is machine learning important? Resurging interest in machine learning is due to the same factors that have made data mining and Bayesian analysis more popular than ever. Things like growing volumes and varieties of available data, computational processing that is cheaper and more powerful, and affordable data storage. Th All of these things mean it's possible to quickly and automatically produce models that can analyze bigger, more complex data and deliver faster, more accurate results – even on a very large scale. And by building precise models, an organization has a better chance of identifying profitable opportunities or avoiding unknown risks. sh What's required to create good machine learning systems? Data preparation capabilities. Algorithms – basic and advanced. Automation and iterative processes. This study source was downloaded by 100000803991717 from CourseHero.com on 06-27-2021 23:34:51 GMT -05:00 https://www.coursehero.com/file/98473585/OOSE-ASSIGN-4docx/ Scalability. Ensemble modeling. In machine learning, a target is called a label. In statistics, a target is called a dependent variable. A variable in statistics is called a feature in machine learning. A transformation in statistics is called feature creation in machine learning. is ar stu ed d vi y re aC s o ou urc rs e eH w er as o. co m SUMMARY OF THE RESEARCH PAPER: sh Th The ubiquity of Machine-learning (ML) techniques has expanded lately. They are being utilized in numerous areas, including network protection, IoT, and self-sufficient vehicles. ML techniques depend on science and computer programming. Science is utilized to create the calculations, foster abilities to gain from input information, and produce agent models. Then again, programming is utilized for execution and hearty execution. Albeit numerous works have explored the science also, software engineering on which ML techniques are fabricated, few have analyzed their execution, which raises numerous worries. The first is the product intricacy of ML techniques. The second is the nature of the accessible executions, including execution and dependability. The third is the nature of the models, which might be adversely affected by a product bug. These worries could be eased if developers could show the product nature of their executions of the ML techniques. Therefore, specialists and experts have been concentrating best practices to design ML frameworks furthermore, programming to resolve issues with programming intricacy and nature of ML techniques. Such practices are frequently formalized as engineering patterns and design patterns by epitomizing reusable answers for normally happening issues inside the given settings in ML frameworks and programming design.— Machine-learning (ML) techniques are turning out to be more pervasive. ML techniques depend on math and programming. Analysts and professionals concentrating best rehearse endeavor to design ML frameworks and programming that location programming intricacy and quality This study source was downloaded by 100000803991717 from CourseHero.com on 06-27-2021 23:34:51 GMT -05:00 https://www.coursehero.com/file/98473585/OOSE-ASSIGN-4docx/ issues. Such design rehearses are frequently formalized as engineering and design patterns by typifying reusable answers for normal issues inside given settings. Nonetheless, a precise report to gather, characterize, also, examine these computer programming (SE) design patterns for ML techniques still can't seem to be accounted for. This gathers great/terrible SE design patterns for ML techniques to give developers an exhaustive characterization of such patterns. In this report the fundamental consequences of a precise writing audit (SLR) of good/terrible design patterns for ML. DISCUSSIONS We describe succinctly two extracted patterns. We omit sh Th is ar stu ed d vi y re aC s o ou urc rs e eH w er as o. co m for the sake of brevity: participants, collaborations, implementation, sample code, and known uses. We then discuss threats to the validity of our results . This study source was downloaded by 100000803991717 from CourseHero.com on 06-27-2021 23:34:51 GMT -05:00 https://www.coursehero.com/file/98473585/OOSE-ASSIGN-4docx/ Powered by TCPDF (www.tcpdf.org)