Avast is a gold sponsor of Machine Learning Prague, the European practical conference about ML, AI, and Deep Learning applications. The event will take place on the 26th and 28th of February, 2021 as a virtual conference. The program promises interesting topics. And experts from Avast cannot be missed there!
Saturday (February 27, 2021) at 1:30 PM CEST
Fireside chat with live Q&A: Deep Learning vs. Rule-based Systems in Practical Applications
Avast experts: Petr Somol (AI Research Director at Avast) and Viliam Lisy ( Principal Scientist at Avast & Associate Professor at Czech Technical University in Prague)
Deep learning has achieved unprecedented performance in a wide range of domains ranging from computer vision, speech recognition, and natural language processing to game playing. However, many industrial systems still rely on human-written and maintain rule-based systems to perform classification. The reasons include better explainability of the rule-based systems and their modularity, which is crucial in dealing with non-stationary problems. We will discuss each approach’s advantages and disadvantages and the possibilities of getting the best of both worlds.
Sunday (February 28, 2021) at 9:30 AM CEST
Presentation: Harnessing relational learning for explainable learning
Avast speaker: Tomas Pevny (Consulting Scientist at Avast)
While most machine learning methods assume that samples are vectors, matrices, or sequences, they have a rich structure in many real-world problems. While this structure makes the manual design of features non-trivial, I see it as an inductive bias that should drive models’ design. In this talk, I will introduce a simple yet powerful framework for learning on structured data. A side yet important feature is the explainability of decisions, which results from ingesting data as-is instead of devising artificial features. A concrete implementation of the framework will be demoed on data from various stages of analysis of malware.
Petr Somol has been active in Machine Learning research for more than 25 years. He obtained his Ph.D. from the Faculty of Mathematics and Physics, Charles University in Prague. He worked as a researcher at Cambridge University, UK, and at the Czech Academy of Sciences. After years of academic research, he moved to industry. Having tasted the work of a Software Engineer at Oracle, he later joined Cisco Systems as Head of Research responsible for developing the Machine Learning based engine underlying Cognitive Threat Analytics. From February 2020, Petr assumes the role of AI Research Director at Avast.
Viliam Lisy is a principal scientist in the Technology and Innovation Office at Avast. He also works as an associate professor at the Artificial Intelligence Center at the Department of Computer Science at the Czech Technical University (CTU) in Prague, where he leads a research group dealing with game theory. He graduated from CTU, Vrije Universiteit in Amsterdam, and Charles University in Prague. He worked as a postdoctoral fellow with Michael Bowling at the University of Alberta in Canada. During his studies, he worked at Carnegie Mellon University, Ben Gurion University, and Phillips Innovation Labs. In his research, Viliam focuses mainly on sequential games with incomplete information and applications of game theory in cybersecurity.
Tomas received his Ph.D. in 2008 from the University of Binghamton, SUNY, USA, where he has pioneered Machine Learning techniques in Steganography and Steganalysis, for which the IEEE Signal Processing Society awarded him. After one year post-doc in Grenoble, France, he has returned to Artificial Intelligence Center at Czech Technical University in Prague. He has extended his interests in Machine Learning problems in cybersecurity. He was closely working with Cognitive Security startup acquired by Cisco Systems Inc. in 2013. Since September 2019, Tomas has been with Avast and Artificial Intelligence Center at Czech Technical University in Prague.