Open AccessTowards Neural-Symbolic AI for Media Understanding
Author(s) -
Polyana B. Costa,
Guilherme Marques,
Arhur C. Serra,
Daniel de Sousa Moraes,
Antonio José G. Busson,
Álan L. V. Guedes,
Guilherme Lazzarotto de Lima,
Sérgio Colcher
Publication year - 2020
Language(s) - English
Resource type - Conference proceedings
DOI - 10.5753/webmedia_estendido.2020.13083
Subject(s) - computer science , artificial intelligence , deep learning , symbolic data analysis , the symbolic , artificial neural network , state (computer science) , natural language processing , multimedia , theoretical computer science , programming language , psychology , psychoanalysis
Methods based on Machine Learning have become state-of-the-art in various segments of computing, especially in the fields of computer vision, speech recognition, and natural language processing. Such methods, however, generally work best when applied to specific tasks in specific domains where large training datasets are available. This paper presents an overview of the state-of-the-art in the area of Deep Learning for Multimedia Content Analysis (image, audio, and video), and describe recent works that propose The integration of deep learning with symbolic AI reasoning. We draw a picture of the future by discussing envisaged use cases that address media understanding gaps which can be solved by the integration of machine learning and symbolic AI, the so-called Neuro-Symbolic integration.