
Abstract: The goal of this session is to demonstrate and learn about building end-to-end pipelines for automated big image classification. The case study explores the business value and impact of transforming a traditional industry, such as insurance, with AI-driven methods using deep learning applied to satellite images. In this session we will describe: The significance of data-strategy and its impact on core business goals; what optimizations can be applied to big image datasets; how to investigate which machine learning algorithm(s) and infrastructure are most suitable for the task; a deep-dive into deep learning and CNNs; and how the final AI-framework is integrated to a company's backend and frontend pipeline. Concepts will be illustrated with examples and case-studies from other major industries involved in the big image transformation.
Bio: Michael Segala is the CEO of SFL Scientific, a data science consulting firm that offers custom development and solutions in data engineering, machine learning, predictive analytics, big data, and artificial intelligence. His firm provides insight into numerous industry-spanning problems, from cancer detection to predictive maintenance. Before founding SFL Scientific, Michael worked as a data scientist in several well-known tech companies, such as Compete Inc. and Akamai Technologies. He holds a PhD in Particle Physics from Brown University.