Biography

I am a Scientist specializing in Big Data and AI on basis of Big Data. I work at TNO with the wide range of domains: from Autonomous cars and ships till Smart Industry and Health sector. I was early adoptor of Big Data movement, and practice it for already 10 years.

Talk

Runtime Modifications of Distributed Big Data AI Models and Its Parameters

There has been phenomenal growth of interest in distributed data analysis with large software and other commercial entities. They are trying to construct the solutions that facilitate flexible, scalable and heterogeneous IT-infrastructures dealing with Big Data analysis. Distributed data processing platforms such as Hadoop or Apache Spark became a de-facto standard in the world of Big Data processing, and in cloud economy. The processing pipelines consisting of AI models for such platforms are composed during design time and then submitted to the central (master) component who then distributes the code among several worker nodes. However, in many situations, the application is not static: the users want to add new processing steps, data scientists adjust parameters of their algorithm, testers find new bugs, requirements from user could change, etc. We propose an approach based on AI Planning to make AI models adaptive within distributed processing pipelines by updating them on-the-fly (runtime) in response to changes coming from AI experts, users, the environment, etc.

Session Keywords