Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Recolector de Cienci...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Closed Access logo, derived from PLoS Open Access logo. This version with transparent background. http://commons.wikimedia.org/wiki/File:Closed_Access_logo_transparent.svg Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao
versions View all 7 versions
addClaim

Proyectos de aprendizaje profundo usando datos regionales

Authors: Heras, Jónathan;

Proyectos de aprendizaje profundo usando datos regionales

Abstract

Debido al impacto de las técnicas de aprendizaje pro-fundo, tanto en entornos industriales como académi-cos, hay una gran demanda de graduados con habilida-des en este campo de la inteligencia artificial. Es poresto que las universidades están comenzando a ofer-tar asignaturas que incluyen temas relacionados con elaprendizaje profundo. En estas asignaturas, las prác-ticas son fundamentales; sin embargo, la mayoría dedichas prácticas tienen dos inconvenientes. El prime-ro es el uso de, o bien, “datos de juguete” que sirvenpara enseñar conceptos pero cuyas soluciones no ge-neralizan a problemas reales; o bien, datos que requie-ren un conocimiento experto para comprender correc-tamente su contexto. En segundo lugar, la mayoría deprácticas de aprendizaje profundo se centran en la ta-rea de entrenar un modelo, y no tienen en cuenta otrastareas, como son la limpieza de los datos o el desplie-gue de los modelos. En este trabajo presentamos unaexperiencia en una asignatura de inteligencia artificialdonde hemos abordado los problemas anteriores usan-do datos del gobierno de la comunidad autónoma don-de se encuentra nuestra universidad. En concreto, losestudiantes han llevado a cabo diversos proyectos devisión por computador y procesado de lenguaje naturalusando técnicas de aprendizaje profundo; por ejemplo,han creado un clasificador de noticias o una aplicaciónpara colorear imágenes antiguas. Compartimos aquí elflujo de trabajo utilizado para organizar la experiencia,las lecciones aprendidas y los retos que pueden encon-trarse al intentar llevar a cabo iniciativas similares.

Due to the impact of Deep Learning both in industryand academia, there is a growing demand of graduates with skills in this field, and Universities are star-ting to offer courses that include Deep Learning subjects. Hands-on assignments that teach students how totackle Deep Learning tasks are an instrumental part ofthose courses. However, most Deep Learning assign-ments have two main drawbacks. First, they use eithertoy datasets that are useful to teach concepts but whosesolutions do not generalise to real problems, or employdatasets that require specialised knowledge to fully understand the problem. Secondly, most Deep Learningassignments are focused on training a model, and donot take into account other stages of the Deep Learning pipeline, such as data cleaning or model deploy-ment. In this work, we present an experience in an Artificial Intelligence course where we have tackled theaforementioned drawbacks by using datasets from theregional council where our University is located. Namely, the students of the course have developed severalcomputer vision and natural language processing pro-jects; for instance, a news classifier or an application tocolourise historical images. We share the workflow fo-llowed to organise this experience, several lessons thatwe have learned, and challenges that can be faced byother instructors that try to conduct a similar initiative.

Country
Spain
Keywords

Experiencia docente, Aprendizaje profundo, Datos regionales, Prácticas

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green