ICS Research Seminar on "Online distributed streaming machine learning"
In the next ICS Research Seminar, Dr. Cristian Axenie will talk about: "Online distributed streaming machine learning: Big Data, Fast Data, All Data"
Abstract: Traditional machine learning algorithms are designed to work on a fixed amount of data. This data is assumed to be stored in files or data bases and all data can be accessed at any time. For many years this traditional batch data processing has been sufficient. But as the amount of data rapidly increases, more and more data gets generated continuously, and consumers are interested in reacting to data drifts in real-time, these traditional approaches reach their limits. Hence machine learning on streams has become an upcoming part of machine learning in the last years. Examples for such environments include sensor networks in IoT, social networks analytics or financial tech. The talk will focus on the core aspects involving this paradigm shift from batch learning on datasets to online learning on streams and cover aspects like Online Learning, Active Learning and One-Shot Learning as well as the shift from strict stable convergence to approximate inference in continuously streams of data. We’ll analyze challenges, trends and state-of-the-art technologies, from neural networks and deep learning to decision trees and distributed clustering.
Bio: After following a robotics and control engineering track during his undergraduate studies, Dr. Axenie joined the Neuroscientific System Theory Group at TU Munich in 2011. During his PhD and Postdoc there, he worked on information processing in neural systems, developed novel multisensory integration algorithms inspired by brain functionality, and transferred these into robotic systems. Starting April 2017 Dr. Axenie joined the Huawei European Research Center as a Senior Research Engineer in Big Data and Machine Learning. His current research focuses on online machine learning algorithms for distributed stream processors.
The seminar will take place at Karlstraße 45, 2. Floor, media room/library, 10h.