DL Research Papers - Academia.edu (original) (raw)

• Top Papers
• Most Cited Papers
• Most Downloaded Papers
• Newest Papers
• People

Deep learning (DL) is a machine learning (ML) subdomain that involves algorithms taken from the brain function named artificial neural networks (ANNs). Recently, DL approaches have gained major accomplishments across various Arabic... more

Deep learning (DL) is a machine learning (ML) subdomain that involves algorithms taken from the brain function named artificial neural networks (ANNs). Recently, DL approaches have gained major accomplishments across various Arabic natural language processing (ANLP) tasks, especially in the domain of Arabic sentiment analysis (ASA). For working on Arabic SA, researchers can use various DL libraries in their projects, but without justifying their choice or they choose a group of libraries relying on their particular programming language familiarity. We are basing in this work on Java and Python programming languages because they have a large set of deep learning libraries that are very useful in the ASA domain. This paper focuses on a comparative analysis of different valuable Python and Java libraries to conclude the most relevant and robust DL libraries for ASA. Throw this comparative analysis, and we find that: TensorFlow, Theano, and Keras Python frameworks are very popular and very used in this research domain.

• • by
  • •
  • Computer Science, Machine Learning, ASA, DL

Deep learning (DL) is a machine learning (ML) subdomain that involves algorithms taken from the brain function named artificial neural networks (ANNs). Recently, DL approaches have gained major accomplishments across various Arabic... more

Deep learning (DL) is a machine learning (ML) subdomain that involves algorithms taken from the brain function named artificial neural networks (ANNs). Recently, DL approaches have gained major accomplishments across various Arabic natural language processing (ANLP) tasks, especially in the domain of Arabic sentiment analysis (ASA). For working on Arabic SA, researchers can use various DL libraries in their projects, but without justifying their choice or they choose a group of libraries relying on their particular programming language familiarity. We are basing in this work on Java and Python programming languages because they have a large set of deep learning libraries that are very useful in the ASA domain. This paper focuses on a comparative analysis of different valuable Python and Java libraries to conclude the most relevant and robust DL libraries for ASA. Throw this comparative analysis, and we find that: TensorFlow, Theano, and Keras Python frameworks are very popular and v...

• • by Yassine AL-AMRANI
  • •
  • Computer Science, Machine Learning, ASA, Electrical Computer Engineering
• • by Diego Riaño
  • •
  • Conservation Biology, Toxicology, Ecology, Bumblebees
• • by Matthew Saunders
  • •
  • Biochemistry, Microbiology, Biophysics, Chemistry
• • by Claudio Sartori
  • •
  • Query Optimization, Description Logic, Data Model, Object Oriented

This paper presents an approach to the problem of mapping ontologies. The motivation for the research stems from the Diogene Project which is developing a web training environment for ICT professionals. The system includes high quality... more

This paper presents an approach to the problem of mapping ontologies. The motivation for the research stems from the Diogene Project which is developing a web training environment for ICT professionals. The system includes high quality training material from registered content providers, and free web material will also be made available through the project's "Web Discovery" component. This involves using web search engines to locate relevant material, and mapping the ontology at the core of the Diogene system to other ontologies that exist on the Semantic Web. The project's approach to ontology mapping is presented, and an evaluation of this method is described.

• • by Ruth Wilson
  • •
  • Computer Science, Information Retrieval, Digital Libraries, Web search

La investigación evaluó el impacto de tres plaguicidas sobre Eisenia fetida en el cultivo de Allium cepa (cebolla) en el distrito de Lurín, Lima, Perú. Se calcularon los valores de dosis letal media (DL50) a los 14 días, porcentaje de... more

La investigación evaluó el impacto de tres plaguicidas sobre Eisenia fetida en el cultivo de Allium cepa (cebolla) en el distrito de Lurín, Lima, Perú. Se calcularon los valores de dosis letal media (DL50) a los 14 días, porcentaje de evasión y actividad alimentaria, y posteriormente la proporción de exposición del tóxico (TER) y el coeficiente de riesgo ambiental (CR) para los plaguicidas zeta-cipermetrina, pendimetalina y profenofos en base a ensayos ecotoxicológicos con E. fetida. Los valores de DL50 a un tiempo de exposición a los 14 días para los tres plaguicidas fueron: zeta-cipermetrina >profenofos >pendimetalina. Se calculó una relación con la dosis de los plaguicidas cercanos a la DL50 para la evasión y para la actividad alimentaria. El valor TER para los tres plaguicidas fue calculado e indicó que no hay impacto ecotoxicológico para E. fetida. Sin embargo, en el valor de CR se presentaron valores de riesgo alto en el total, donde la zeta-cipermetrina indicó el 92,77%...

• • by Diego Elias Estremadoyro
  • •
  • Riesgo Ambiental, Eisenia Fetida, DL
• • by Mike S Jackson
  • •
  • Computer Science, Digital Libraries, DL
• • by Luis Rocha
  • •
  • DL

This article describes the Compus visualization system that assists in the exploration and analysis of structured document corpora encoded in XML. Compus has been developed for and applied to a corpus of 100 French manuscript letters of... more

This article describes the Compus visualization system that assists in the exploration and analysis of structured document corpora encoded in XML. Compus has been developed for and applied to a corpus of 100 French manuscript letters of the 16th century, transcribed and encoded for scholarly analysis using the recommendations of the Text Encoding Initiative. By providing a synoptic visualization of

• • by Nicole Dufournaud
  • •
  • History, Digital Libraries, Information Visualization, XML

Wehave constructed a proof-of-principle system for supporting collaborative forensic medicine. The early prototype is built on ABC/DGS, a graph-server and collaborativehypermedia system built in the UNC Collaboratory. A second prototype... more

Wehave constructed a proof-of-principle system for supporting collaborative forensic medicine. The early prototype is built on ABC/DGS, a graph-server and collaborativehypermedia system built in the UNC Collaboratory. A second prototype is underway that has more flexible control of multi-person creation of, and access to, the shared patient data and pathology artifacts. Created with Dewan's Suite, this version maintains consistentyet different independent views of the underlying data, and moderates access through these views. We conclude by describing a planned third prototype, to be built not on ABC, but on a modification of the WWW httpd distributed data server.

• • by Kevin Jeffay
  • •
  • Forensic Medicine, World Wide Web, DL