Evaluating learning algorithms and classifiers

Lavesson, Niklas; Davidsson, Paul

doi:10.1504/ijiids.2007.013284

Cited by 19 publications

(19 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They concluded that the artificial intelligence is a combination of reasoning, learning, perception, linguistic approach and problem solving. Niklas Lavesson [3] also have described about the supervised type of machine learning .The ambition of this review is to introduce the types of machine learning such as supervised, unsupervised and reinforcement etc. The review also explores the applications of AI and machine learning in real time.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Review Paper on General Concepts of “Artificial Intelligence and Machine Learning”

Rupali¹,

Patil²

2017

International Advanced Research Journal in Science, Engineering

View full text Add to dashboard Cite

Long days ago, there was all kind of work which is only done by the humans. There were no such machines and technologies like today. At that time, science is not developed and technologies were not invented. So the working is totally dependent on the peoples and humans have recognised that "Today"s science is the tomorrow"s technology". New superiorly advanced technologies are not less than blessing of god. Adaptive inventions for reducing the human work and bright future were invented which is simply called as Artificial Intelligence and Machine learning. Even though there were many false assumptions at the early beginning, we are witnessing a new era of errorless technology and superior science. This review involves the general concepts of artificial intelligence and machine learning.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Machine learning is one of the most important technical approaches to AI and the basis of many recent advances and commercial applications of AI. Modern machine learning is a statistical process that helps to define the output and future use of data [3]. There are following types of learning: 1.…”

Section: Figiva Diagram Representing Machine Learning Mechanismmentioning

confidence: 99%

A Review Paper on General Concepts of “Artificial Intelligence and Machine Learning”

Rupali¹,

Patil²

2017

International Advanced Research Journal in Science, Engineering

View full text Add to dashboard Cite

show abstract

“…However, quality attributes can be defined at a number of abstraction levels. For example, depending on the characteristics of the problem, one might need to evaluate training-related (algorithmic) properties or testing-related (classifierspecific) properties (Lavesson and Davidsson, 2007). Moreover, some attributes can only be subjectively evaluated while others are associated with objective metrics.…”

Section: Identification Of Quality Attributesmentioning

confidence: 99%

A method for evaluation of learning components

et al. 2013

Self Cite

View full text Add to dashboard Cite

Today, it is common to include machine learning components in software products. These components offer specific functionalities such as image recognition, time series analysis, and forecasting but may not satisfy the non-functional constraints of the software products. It is difficult to identify suitable learning algorithms for a particular task and software product because the non-functional requirements of the product affect algorithm suitability. A particular suitability evaluation may thus require the assessment of multiple criteria to analyse trade-offs between functional and non-functional requirements. For this purpose, we present a method for APPlication-Oriented Validation and Evaluation (APPrOVE). This method comprises four sequential steps that address the stated evaluation problem. The method provides a common ground for different stakeholders and enables a multi-expert and multi-criteria evaluation of machine learning algorithms prior to inclusion in software products.

show abstract

“…However, quality attributes can be defined on a number of abstraction levels. For example, depending on the characteristics of the problem, one may need to evaluate training-related (algorithmic) properties or testingrelated (classifier-specific) properties [10]. Moreover, some attributes can only be subjectively evaluated while others are associated with objective metrics.…”

Section: A Identification Of Quality Attributesmentioning

confidence: 99%

“…The question of how to select a suitable metric for a specific quality attribute is out of scope in this paper. There are many studies to refer to for readers interest in this topic (see, for example [1], [10]). For the purpose of the presented framework, it is sufficient to know that several aspects need to be taken into account when selecting metrics for a particular quality attribute.…”

Section: Selection Of Metricsmentioning

confidence: 99%