no code implementations • 19 Jan 2023 • Axel Ciceri, Thomas Fischbacher
We discuss the problem of numerically backpropagating Hessians through ordinary differential equations (ODEs) in various contexts and elucidate how different approaches may be favourable in specific situations.
no code implementations • ICLR 2021 • Thomas Fischbacher, Luciano Sbaiz
Quantum computing-based machine learning mainly focuses on quantum computing hardware that is experimentally challenging to realize due to requiring quantum gates that operate at very low temperature.
no code implementations • 10 Aug 2020 • Thomas Fischbacher, Iulia M. Comsa, Krzysztof Potempa, Moritz Firsching, Luca Versari, Jyrki Alakuijala
We present a novel machine learning architecture that uses the exponential of a single input-dependent matrix as its only nonlinearity.
4 code implementations • 30 Jul 2019 • Iulia M. Comsa, Krzysztof Potempa, Luca Versari, Thomas Fischbacher, Andrea Gesmundo, Jyrki Alakuijala
The timing of individual neuronal spikes is essential for biological brains to make fast responses to sensory stimuli.
no code implementations • 1 Jun 2019 • Iulia M. Comsa, Moritz Firsching, Thomas Fischbacher
Using de Wit-Nicolai $D=4\;\mathcal{N}=8\;SO(8)$ supergravity as an example, we show how modern Machine Learning software libraries such as Google's TensorFlow can be employed to greatly simplify the analysis of high-dimensional scalar sectors of some M-Theory compactifications.
no code implementations • ICLR 2019 • Lukas Balles, Thomas Fischbacher
We introduce an analytic distance function for moderately sized point sets of known cardinality that is shown to have very desirable properties, both as a loss function as well as a regularizer for machine learning applications.