Filters








36 Hits in 3.7 sec

ML-Schema: Exposing the Semantics of Machine Learning with Schemas and Ontologies [article]

Gustavo Correa Publio, Diego Esteves, Agnieszka Ławrynowicz, Panče Panov, Larisa Soldatova, Tommaso Soru, Joaquin Vanschoren, Hamid Zafar
2018 arXiv   pre-print
We argue that exposing semantics of machine learning algorithms, models, and experiments through a canonical format may pave the way to better interpretability and to realistically achieve the full interoperability  ...  on machine learning algorithms, datasets, and experiments.  ...  Instead, MEX is designed to provide a simple and lightweight vocabulary for exchanging basic machine learning metadata in order to achieve a high level of interoperability.  ... 
arXiv:1807.05351v1 fatcat:xdvadcczlbhy5evoajnc7k3fea

MEX vocabulary

Diego Esteves, Diego Moussallem, Ciro Baron Neto, Tommaso Soru, Ricardo Usbeck, Markus Ackermann, Jens Lehmann
2015 Proceedings of the 11th International Conference on Semantic Systems - SEMANTICS '15  
However, the Linked Data community still misses a lightweight specification for interchanging machine-learning metadata over different architectures to achieve a higher level of interoperability.  ...  In order to compare machine-learning experiment results with each other and collaborate positively, they need to be performed thoroughly on the same computing environment, using the same sample datasets  ...  for exchanging machine learning metadata to achieve a higher level of interoperability.  ... 
doi:10.1145/2814864.2814883 dblp:conf/i-semantics/EstevesMNSUAL15 fatcat:seq7mmhrqnhn5o4lkzf527bjdq

Semantic Data Ingestion for Intelligent, Value-Driven Big Data Analytics

Jeremy Debattista, Judie Attard, Rob Brennan
2018 2018 4th International Conference on Big Data Innovations and Applications (Innovate-Data)  
In this position paper we describe a conceptual model for intelligent Big Data analytics based on both semantic and machine learning AI techniques (called AI ensembles).  ...  These processes are linked to business outcomes by explicitly modelling data value and using semantic technologies as the underlying mode for communication between the diverse processes and organisations  ...  We envisage a need for wider and more diverse ensembles than the ones that are currently used in machine learning or data science, spanning currently fragmented AI approaches [2] .  ... 
doi:10.1109/innovate-data.2018.00008 dblp:conf/obd/DebattistaAB18 fatcat:3hiyg2rd4fh2hdx37jelozkz5e

The Use of Open Data to Improve the Repeatability of Adaptivity and Personalisation Experiment

Harshvardhan J. Pandit, Roghaiyeh Gachpaz Hamed, Séamus Lawless, Dave Lewis
2019 Zenodo  
of metadata using linked open data vocabularies.  ...  The use of an expressive ontology provides an interoperable and unambiguous record of the workflow interlinked with the resulting data set.  ... 
doi:10.5281/zenodo.3244366 fatcat:ehqgsigclzda3d5474ej5347oq

The Use of Open Data to Improve the Repeatability of Adaptivity and Personalisation Experiment

Harshvardhan J. Pandit, Roghaiyeh Gachpaz Hamed, Shay Lawless, David Lewis
2016 User Modeling, Adaptation, and Personalization  
of metadata using linked open data vocabularies.  ...  The use of an expressive ontology provides an interoperable and unambiguous record of the workflow interlinked with the resulting data set.  ... 
dblp:conf/um/PanditHLL16 fatcat:nc2iveyw7jd43miwi7vwvpmyga

The Use of Open Data to Improve the Repeatability of Adaptivity and Personalisation Experiment

Harshvardhan J. Pandit, Roghaiyeh Gachpaz Hamed, Séamus Lawless, Dave Lewis
2019 Zenodo  
of metadata using linked open data vocabularies.  ...  The use of an expressive ontology provides an interoperable and unambiguous record of the workflow interlinked with the resulting data set.  ... 
doi:10.5281/zenodo.3245325 fatcat:qzretjxzojccbmdsqdymdagnke

The role of metadata in reproducible computational research [article]

Jeremy Leipzig, Daniel Nüst, Charles Tapley Hoyt, Stian Soiland-Reyes, Karthik Ram, Jane Greenberg
2021 arXiv   pre-print
Metadata provides context and provenance to raw data and methods and is essential to both discovery and validation.  ...  This potential and wide-support for the FAIR principles have motivated interest in metadata standards supporting RCR.  ...  MEX is designed as a vocabulary to describe the components of machine learning workflows.  ... 
arXiv:2006.08589v2 fatcat:txxkodvwezc6bcdngu3by6wnni

Managing Machine Learning Workflow Components [article]

Marcio Moreno, Vítor Lourenço, Sandro Rama Fiorini, Polyana Costa, Rafael Brandão, Daniel Civitarese, Renato Cerqueira
2020 arXiv   pre-print
Machine Learning Workflows (MLWfs) have become essential and a disruptive approach in problem-solving over several industries.  ...  To handle this problem, in this paper, we introduce machine learning workflow management (MLWfM) as a technique to aid the development and reuse of MLWfs and their components through three aspects: representation  ...  To overcome this issue, the W3C ML-Schema [11] extends the MEX vocabulary improving the representation of the machine learning process.  ... 
arXiv:1912.05665v2 fatcat:lvw6urp2tvbk3nu2zopn4ipqii

Semantic Description of Data Mining Datasets: An Ontology-Based Annotation Schema [chapter]

Ana Kostovska, Sašo Džeroski, Panče Panov
2020 Lecture Notes in Computer Science  
We demonstrate the utility of these annotations in two use cases: semantic annotation of remote sensing data and data about neurodegenerative diseases.  ...  The data and the metadata have to be interoperable with external data from the same domain.  ...  The Exposé ontology provides the vocabulary needed for a detailed description of machine learning experiments. MEX represents a lightweight interchange format for ML experiments.  ... 
doi:10.1007/978-3-030-61527-7_10 fatcat:7trft2tijffplbfc5xjqsz56i4

Semantic Annotation of Predictive Modelling Experiments [chapter]

Ilin Tolovski, Sašo Džeroski, Panče Panov
2020 Lecture Notes in Computer Science  
Here, we showcase the capabilities of the system with executing multi-target regression experiment on a water quality prediction dataset using the Clus software.  ...  Introduction Data mining and machine learning experiments are conducted in higher volume than ever before, in various settings and domains.  ...  Storing the data in communitypreferred and versatile archival format combined with the use of standardized vocabulary helps us score 2/2 points for the interoperability of our metadata.  ... 
doi:10.1007/978-3-030-61527-7_9 fatcat:ii5fgx3shzgbbnuzxeotfufrhi

Prototipo de un sistema gestor de objetos de aprendizaje para ciencias agrícolas (SIGEOACA)

Ivonne Del Rosario Montes Tierrablanca, José Luis García Cué, David H. Del Valle Paniagua, Reyna Carolina Medina Ramírez
2017 Revista Mexicana de Ciencias Agrícolas  
activities, evaluation and with one or more identifiers (metadata) that will be used for later search and use, able to be assembled in different teaching-learning situations and can be used within an  ...  Analysis: a literature review was made for the identification of learning objects, their pedagogical, technological and international standards used in metadata.  ... 
doi:10.29312/remexca.v8i1.69 fatcat:6p4tinvl5nhxhiabdkrgbcr2jy

Integrating the Management of Personal Data Protection and Open Science with Research Ethics

Dave Lewis, Joss Moorkens, Kaniz Fatema
2017 Proceedings of the First ACL Workshop on Ethics in Natural Language Processing  
We analyse the challenges that arise and the opportunities to address many of them through the use of existing open data practices for sharing language research data.  ...  This approach is amenable to extension with domain-specific experimental metadata, such as the machine learning metadata proposed in the MEX vocabulary (Esteves et al., 2015) .  ...  Machine translation (MT) is another popular LT technique use in translation practice.  ... 
doi:10.18653/v1/w17-1607 dblp:conf/ethnlp/LewisMF17 fatcat:fqrv4thzybbd5hysnexd4ebtyi

A Brave New World: Archivists and Shareable Descriptive Metadata

Jenn Riley, Kelcy Shepherd
2009 The American Archivist  
That EAD is an XML schema is a benefit for archivists wanting flexible, interoperable descriptive metadata.  ...  technical protocols for machine-to-machine sharing of metadata, including the Open Archives Initiative Protocol for Metadata Harvesting (OAI PMH). 24 Large-scale metadata aggregators such as OAIster 25  ... 
doi:10.17723/aarc.72.1.kl70j01223654874 fatcat:ztacfydvuff6pd6fqv7mpdbeoi

Semantic Descriptor for Intelligence Services

Edgar Ramos, Timon Schneider, Marie-J. Montpetit, Ben De Meester
2020 2020 International Conferences on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData) and IEEE Congress on Cybermatics (Cybermatics)  
In this article, it a semantic description of functions is proposed and used to provide intelligence services mainly for networked devices.  ...  The semantic descriptors aim to provide interoperability between multiple domains' vocabularies, data models, and ontologies, so that device applications become able to deploy them autonomously once they  ...  Several state-of-the-art projects are aimed at semantically describe data mining and machine learning algorithms and experiments in order to improve their interoperability and support model selection.  ... 
doi:10.1109/ithings-greencom-cpscom-smartdata-cybermatics50389.2020.00027 fatcat:qui5zsq2kffjfdv3jjad3hyfge

Experimenting with reproducibility in bioinformatics [article]

Yang-Min Kim, Jean-Baptiste Poline, Guillaume Dumas
2017 bioRxiv   pre-print
Here, we present a case study of our attempt to reproduce a promising bioinformatics method [1] and illustrate the challenges to use a published method for which code and data were available.  ...  For instance in the field of machine learning, standard image databases are widely used for training and testing (e.g. MNIST for handwritten digits [35] ).  ...  We tried to comply with open source coding standards and to learn how to efficiently use Git and GitHub.  ... 
doi:10.1101/143503 fatcat:m5zmfdhcorgytcptl3sgo3i7qy
« Previous Showing results 1 — 15 out of 36 results