no code implementations • 21 Feb 2020 • Mayank Mittal, Marco Gallieri, Alessio Quaglino, Seyed Sina Mirrazavi Salehian, Jan Koutník
With a growing interest in data-driven control techniques, Model Predictive Control (MPC) provides an opportunity to exploit the surplus of data reliably, particularly while taking safety and stability into account.
no code implementations • 15 Nov 2019 • Marco Gallieri, Seyed Sina Mirrazavi Salehian, Nihat Engin Toklu, Alessio Quaglino, Jonathan Masci, Jan Koutník, Faustino Gomez
A min-max control framework, based on alternate minimisation and backpropagation through the forward model, is used for the offline computation of the controller and the safe set.
no code implementations • ICLR 2020 • Alessio Quaglino, Marco Gallieri, Jonathan Masci, Jan Koutník
This paper proposes the use of spectral element methods \citep{canuto_spectral_1988} for fast and accurate training of Neural Ordinary Differential Equations (ODE-Nets; \citealp{Chen2018NeuralOD}) for system identification.
5 code implementations • ICML 2017 • Julian Georg Zilly, Rupesh Kumar Srivastava, Jan Koutník, Jürgen Schmidhuber
We introduce a novel theoretical analysis of recurrent networks based on Gersgorin's circle theorem that illuminates several modeling and optimization issues and improves our understanding of the LSTM cell.
Ranked #16 on Language Modelling on Hutter Prize
no code implementations • 29 Jan 2016 • Michael Wand, Jan Koutník, Jürgen Schmidhuber
Lipreading, i. e. speech recognition from visual-only recordings of a speaker's face, can be achieved with a processing pipeline based solely on neural networks, yielding significantly better accuracy than conventional methods.
15 code implementations • 13 Mar 2015 • Klaus Greff, Rupesh Kumar Srivastava, Jan Koutník, Bas R. Steunebrink, Jürgen Schmidhuber
Several variants of the Long Short-Term Memory (LSTM) architecture for recurrent neural networks have been proposed since its inception in 1995.
5 code implementations • 14 Feb 2014 • Jan Koutník, Klaus Greff, Faustino Gomez, Jürgen Schmidhuber
Sequence prediction and classification are ubiquitous and challenging problems in machine learning that can require identifying complex dependencies between temporally distant inputs.