Machine Learning and its applications

On Thursday October 27, 2022 our Head Prof. Enrique Zuazua will talk on “Control and Machine Learning” as invited speaker at the Machine Learning and Its Applications from October 10th. to 28th, 2022 at Institute for Mathematical Sciences National University of Singapore.

Abstract. In this lecture we shall present some recent results on the interplay between control and Machine Learning, and more precisely, Supervised Learning and Universal Approximation.
We adopt the perspective of the simultaneous or ensemble control of systems of Residual Neural Networks (ResNets). Roughly, each item to be classified corresponds to a different initial datum for the Cauchy problem of the ResNets, leading to an ensemble of solutions to be driven to the corresponding targets, associated to the labels, by means of the same control.

We present a genuinely nonlinear and constructive method, allowing to show that such an ambitious goal can be achieved, estimating the complexity of the control strategies. This property is rarely fulfilled by the classical dynamical systems in Mechanics and the very nonlinear nature of the activation function governing the ResNet dynamics plays a determinant role. It allows deforming half of the phase space while the other half remains invariant, a property that classical models in mechanics do not fulfill. The turnpike property is also analyzed in this context, showing that a suitable choice of the cost functional used to train the ResNet leads to more stable and robust dynamics.

This lecture is inspired in joint work, among others, with Borjan Geshkovski (MIT), Carlos Esteve (Cambridge), Domenec Ruiz-Balet (IC, London) and Dario Pighin (Sherpa.ai)

WHERE

Talk: Control & Machine Learning by E. Zuazua (10:15H -Singapore time, GMT+8)

Online: Zoom meeting link
Meeting ID: 814 6599 9333 | PIN code: 8401010

On-site: IMS Auditorium
Institute for Mathematical Sciences. National University of Singapore
3 Prince George’s Park. Singapore 118402

The aim of this workshop is to bring together researchers in theoretical and applied machine learning, to share their work and to explore collaborative opportunities on:
-Deep Learning Theory
-Machine Learning Applications in Physical/Biological Sciences
-Bayesian Approaches in Machine Learning
-Interpretability, Fairness and Privacy in Machine Learning
-Reinforcement Learning Theory

Check the program and all details at the official page of the event

The event is finished.

Date

Thu. Oct 27, 2022
Expired!

Time

04:15 - 05:00

Speaker