Research Scientist at NNAISENSE, Lugano
DEIB - Alario Seminar Room (building 21)
June 22nd, 2018
2.00 pm
Contacts:
Matteo Matteucci
Research Line:
Artificial intelligence and robotics
NNAISENSE has a long lasting record of ground-breaking results in artificial intelligence (AI). From perception to reinforcement learning, the company’s legacy of super-human performance places them in the right position to take AI technology into everyday control systems. While AI approaches control problems from an information theoretical and statistical perspective, control theory addresses issues concerning the physical world with a strong focus on safety, hard constraints and theoretical guarantees. While control approaches can be very robust they can seldom suffer from conservativeness of their assumptions. This is believed not to be the case for AI, where performance depends mainly on the quality and the amount of data but no general guarantees exist for safety. For this reason, while deep learning is becoming the industry standard for perception, its use in control is mostly limited to simulated or non-critical tasks. Combining the fields of control and AI has the potential for retaining best of both Worlds. The first part of the talk will briefly introduce NNAISENSE’s research objectives in this direction. In the second part, we will then introduce Non-Autonomous Input-Output Stable Network (NAIS-Net): a very deep architecture, developed in collaboration with Polimi, where each stacked processing block is derived from a time-invariant non-autonomous dynamical system. Non-autonomy is implemented by skip connections from the block input to each of the unrolled processing stages and allows stability to be enforced so that blocks can be unrolled adaptively to a pattern-dependent processing depth. NAIS-Net induces non-trivial, Lipschitz input-output maps, even for an infinite unroll length. We prove that the network is globally asymptotically stable so that for every initial condition there is exactly one input-dependent equilibrium assuming tanh units, and multiple stable equilibria for ReL units. An efficient implementation that enforces the stability under derived conditions for both fully-connected and convolutional layers is also presented.
Experimental results show how NAIS-Net exhibits stability in practice, yielding a significant reduction in generalization gap compared to ResNets.
Marco Gallieri is a Research Scientist at NNAISENSE, in Lugano. He received a PhD in Engineering from Sidney Sussex College, the University of Cambridge, in 2014. His PhD Thesis was on LASSO-MPC and is published by Springer. In 2009 he received an MSc in automation engineering from the Universita’ Politecnica delle Marche, in Italy. He wrote his MSc thesis during a visiting term at the National University of Ireland, Maynooth. In 2010 he was a Marie Curie early stage researcher at the Instituto Superior Tecnico in Lisbon working on non-linear control of autonomous underwater vehicles. Before joining NNAISENSE, he spent three years with the McLaren group, where he developed a model based Li-Ion battery management system for the F1 power unit and a prototype for next generation F1 driver-in-the-loop simulator. He then worked as a data scientist in the R&D branch of the group where he led the development of a wearable technology.
He’s currently leading the control theory R&D efforts of NNAISENSE. His research interests are at the intersection between control and machine learning and include the study of stability of deep and recurrent neural networks as well as their use in control systems for safety-critical applications.