Antonio R. Paiva received the licenciatura degree in electronics and telecommunications engineering from the University of Aveiro, Portugal in 2003, and the M.S. and Ph.D. degrees in electrical and computer engineering from the University of Florida in 2005 and 2008, respectively.
Between 2003 and 2004 he was a research assistant at the Institute of Electronics and Telematics Engineering at the University of Aveiro working on image compression. From 2008 to 2010, he worked at the SCI Institute at the University of Utah as a post-doctoral fellow on the application of machine learning to cell segmentation and neural circuit reconstruction from 3D electron microscopy image volumes. In 2010, he joined the ExxonMobil Upstream Research Company as a research specialist working on pattern recognition analysis of 3D seismic and well logs geophysical data, and later became a team lead working to complete and transfer several research capabilities into production software. In 2015, he became a research associate at Corporate Strategic Research, ExxonMobil Research and Engineering. He is now a Principal Data Scientist at Allstate Insurance. He has led numerous projects and developed novel machine learning methods for several applications. Business use cases include volumetric image analysis, fault detection in chemical processes, safety data analytics, microbial growth modeling, bioinformatics, and uncertainty quantification in geophysical inverse problems. He is a past Associate Editor for the IEEE Transactions on Neural Networks and Learning Systems, and a past Associate Editor of the IEEE Signal Processing Letters.
His research interests span several areas within machine learning, pattern recognition, and adaptive signal processing. Most notably, these include probabilistic deep learning models, kernel methods, information-theoretic learning, and fast algorithms for machine learning.
Antonio Paiva is a Principal Data Scientist with Allstate with more than 14 years of experience in machine learning research. His research has targeted a number of application areas, including kernels methods for neurophysiology data, neural network segmentation of microscopy image volumes, pattern recognition of geophysical image volumes, and probabilistic modeling of biological and physical processes. He is a past Associate Editor of the IEEE Transactions on Neural Networks and Learning Systems and the IEEE Signal Processing Letters journals.