Symposium on Machine Learning and Dynamical Systems, Imperial College London, Feb. 11-13, 2019

Since its inception in the 19th century through the efforts of Poincaré and Lyapunov, the theory of dynamical systems addresses the qualitative behaviour of dynamical systems as understood from models. From this perspective, the modeling of dynamical processes in applications requires a detailed understanding of the processes to be analyzed. This deep understanding leads to a model, which is an approximation of the observed reality and is often expressed by a system of Ordinary/Partial, Underdetermined (Control), Deterministic/Stochastic differential or difference equations. While models are very precise for many processes, for some of the most challenging applications of dynamical systems (such as climate dynamics, brain dynamics, biological systems or the financial markets), the development of such models is notably difficult.

On the other hand, the field of machine learning is concerned with algorithms designed to accomplish a certain task, whose performance improves with the input of more data. Applications for machine learning methods include computer vision, stock market analysis, speech recognition, recommender systems and sentiment analysis in social media. The machine learning approach is invaluable in settings where no explicit model is formulated, but measurement data is available. This is frequently the case in many systems of interest, and the development of data-driven technologies is becoming increasingly important in many applications.

The intersection of the fields of dynamical systems and machine learning is largely unexplored, and the goal of this symposium is to bring together researchers from these fields to fill the gap between the theories of dynamical systems and machine learning in the following directions:

  • Machine Learning for Dynamical Systems: how to analyze dynamical systems on the basis of observed data rather than attempt to study them analytically.
  • Dynamical Systems for Machine Learning: how to analyze algorithms of Machine Learning using tools from the theory of dynamical systems.

Organizers: Boumediene Hamzi, Yi-Ke Guo, Jeroen Lamb, Diana O'Malley (Imperial College London) and Robert MacKay (University of Warwick and The Alan Turing Institute)

Preregistration can be made here

A book of abstracts can be found here
Slides: Just click on the speaker's name in the agenda below.
A Pamphlet can be found here
The list of participants can be found here
Some pictures of the event can be found herehere and here

Food and Refreshments: During all days, morning and afternoon drinks and snacks are provided during dedicated Refreshment Breaks. Additionally, we provide:
Monday 11 February:
13:00-14:00 hot & cold buffet lunch in the foyer of the Alexander Fleming Building.
18:30-19:30 drinks and snacks at reception after the DSI distinguished lecture
Tuesday 12 February:
18:30-20:30 Symposium dinner at the Polish Club “Ognisko”, 57 Exhibition Road.

Participants are advised to make their own arrangements during the Lunch Breaks on Tuesday 12 February and Wednesday 13 February, 13:00-14:00. There are various food outlets on campus. More details can be found here.

Wifi:                                     At Imperial College you can have wifi internet access through eduroam. Alternatively, you can set up a temporary wifi account using the link
and logging in with the username "conf78997", upon which you will be entering a kiosk mode, where you can register your own account. This login account will provide you wifi access at Imperial College only during the period 11-13 Feb.

Location of sessions (a map of these locations can be found here)
Monday 11th February
Conference Location: SAFB (Sir Alexander Fleming Building) G16 LT1 - 
Poster session: 4:15pm – 5:15pm
Location: C&G (City & Guilds Building) Foyer
Evening Lecture in C&G (City & Guilds Building) LT200 - 5.30pm-6:30pm
Location: C&G LT200
Tuesday 12th February
Conference Location: Pippard LT, Level 5, Sherfield Building
Wednesday 13th February
Conference Location: Pippard LT, Level 5, Sherfield Building