Recent Advances in Big Data and Deep Learning_ Proceedings of the INNS Big Data and Deep Learning Conference INNSBDDL2019.pdf

Luca Oneto · Nicolò Navarin · Alessandro Sperduti · Davide Anguita Editors Proceedings of the International Neural Networks Society 1 Series Editors: Plamen Angelov · Robert Kozma Recent Advances in Big Data and Deep Learning Proceedings of the INNS Big Data and Deep Learning Conference, INNSBDDL2019, held at Sestri Levante, Genova, Italy, 16–18 April, 2019 Proceedings of the International Neural Networks Society Volume 1 Series Editors Plamen Angelov, School of Computing and Communications, University of Lancaster, Lancaster, UK Robert Kozma, Optimization and Networks Department, University of Memphis, Memphis, TN, USA The“Proceedings of the International Neural Networks Society INNS”publishes research contributions on fundamental principles and applications related to neural networks and modeling behavioral and brain processes. Topics of interest include new developments, state-of-art theories, methods and practical applications, covering all aspects of neural networks and neuromorphic technologies for (artificially; replace with anthropomorphic) intelligent (designs; replace with systems). This series covers high quality books that contribute to the full range of neural networks research, from computational neuroscience, cognitive science, behavioral and brain modeling, (add machine) learning algorithms, mathematical theories, to technological applications of systems that significantly use neural network concepts and techniques. The series publishes monographs, contributed volumes, lecture notes, edited volumes, and conference proceedings in neural networks spanning theoretical, experimental, computational, and engineering aspects. Submissions of highly innovative cutting-edge contributions are encouraged, which extend our under- standing at the forefront of science going beyond mainstream approaches. Of particular value to both the contributors and the readership are the short publication timeframe and the world-wide distribution, which enable both wide and r