No próximo dia 7 de Abril, pelas 11h00 na sala FC6 029 do DCC FCUP, Birk Torpmann-Hagen irá dar uma palestra intitulada "Runtime Assurance of Deep Neural Networks".
A palestra é organizada pelo DCC-FCUP.
Short Bio
Birk Torpmann-Hagen is a final year PhD student at UiT: The Arctic University of Tromsø, in collaboration with SimulaMet. His thesis explores methods for detecting and characterizing distributional shift and how these methods can be leveraged towards computing credible and precise performance estimates at runtime. He has spent 5 semesters as a teaching assistant in courses covering AI, image analysis, and mechatronics, and has interned at the Norwegian Defence Research Institute (FFI) and Domos, a tech start-up based in Oslo. His primary research interests are generalization in deep learning, malware in neural networks, and distributional shift detection.
Title
Runtime Assurance of Deep Neural Networks
Abstract
Despite attaining excellent performance on benchmarks, deep neural networks are known to fail in deployment scenarios. This phenomenon can largely be attributed to the sensitivity of neural networks to minor and even imperceptible shifts in the nature of the input data, often referred to as distributional shifts. These shifts are common in real-world scenarios but are rarely accounted for in evaluations, often resulting in inflated performance metrics that misrepresent the performance of the network. Effective and responsible deployment thus requires accounting for the incidence of distributional shifts. This presentation represents a summary of my research to this end and encompasses the development of a comprehensive toolset for the runtime verification, evaluation, and risk-assessment of deep neural networks at runtime.