On the Universal Transformation of Data-Driven Models to Control Systems

Duration: 22 mins 56 secs

Share this media item:

Embed this media item:

<iframe width="_width_" height="_height_" src="https://sms.cam.ac.uk/media/3708962/embed" frameborder="0" scrolling="no" allowfullscreen></iframe>

Choose size:

About this item

Available Formats

About this item

Description:	Junior Professor Doctor Sebastian Peitz (Universität Paderborn) 19th November 2021 \| 15:00 - 15:30


Created:	2021-11-22 14:37
Collection:	Modelling Behaviour to Inform Policy for Pandemics
Publisher:	Isaac Newton Institute for Mathematical Sciences
Copyright:	Junior Professor Doctor Sebastian Peitz
Language:	eng (English)


Abstract:	As in almost every other branch of science, the advances in data science and machine learning have also resulted in improved modeling and simulation of nonlinear dynamical systems. In many cases, predictive methods are advertised to ultimately be useful for control. However, the question of how to use a predictive model for control is left unanswered in many cases due to the associated challenges, namely a significantly higher system complexity, the requirement of much larger data sets and an increased and often problem-specific modeling effort. To solve these issues, we present a universal framework to transform arbitrary predictive models into control systems and use them for feedback control. The advantages are a linear increase in data requirements with respect to the control dimension, performance guarantees that rely exclusively on the accuracy of the predictive model, and only little prior knowledge requirements in control theory to solve complex control problems.

Abstract:

As in almost every other branch of science, the advances in data science and machine learning have also resulted in improved modeling and simulation of nonlinear dynamical systems. In many cases, predictive methods are advertised to ultimately be useful for control. However, the question of how to use a predictive model for control is left unanswered in many cases due to the associated challenges, namely a significantly higher system complexity, the requirement of much larger data sets and an increased and often problem-specific modeling effort. To solve these issues, we present a universal framework to transform arbitrary predictive models into control systems and use them for feedback control. The advantages are a linear increase in data requirements with respect to the control dimension, performance guarantees that rely exclusively on the accuracy of the predictive model, and only little prior knowledge requirements in control theory to solve complex control problems.

Available Formats

Format	Quality	Bitrate	Size
MPEG-4 Video	1280x720	2.54 Mbits/sec	437.05 MB	View	Download
MPEG-4 Video	640x360	876.99 kbits/sec	147.31 MB	View	Download
WebM	1280x720	1.37 Mbits/sec	236.74 MB	View	Download
WebM	640x360	372.5 kbits/sec	62.61 MB	View	Download
iPod Video	480x270	482.05 kbits/sec	80.97 MB	View	Download
MP3	44100 Hz	249.79 kbits/sec	42.02 MB	Listen	Download
Auto *	(Allows browser to choose a format it supports)