no code implementations • 28 Mar 2023 • Jakob Kaiser, Raphael Stock, Eric Müller, Johannes Schemmel, Sebastian Schmitt
In contrast to other optimization methods such as genetic algorithms or stochastic searches, the SNPE algorithms belongs to the class of approximate Bayesian computing (ABC) methods and estimates the posterior distribution of the model parameters; access to the posterior allows classifying the confidence in parameter estimations and unveiling correlation between model parameters.
no code implementations • 22 Mar 2023 • Hartmut Schmidt, José Montes, Andreas Grübl, Maurice Güttler, Dan Husmann, Joscha Ilmberger, Jakob Kaiser, Christian Mauch, Eric Müller, Lars Sterzenbach, Johannes Schemmel, Sebastian Schmitt
The first-generation of BrainScaleS, also referred to as BrainScaleS-1, is a neuromorphic system for emulating large-scale networks of spiking neurons.
no code implementations • 13 Jan 2023 • Felix Lanfermannn, Sebastian Schmitt, Patricia Wollstadt
To support the novel understanding of concept identification, we consider a simulated data set from a decision-making problem in the energy management domain and show that the identified clusters are more interpretable with respect to relevant feature subsets than clusters found by common clustering algorithms and are thus more suitable to support a decision maker.
no code implementations • 25 Aug 2022 • Xilu Wang, Yaochu Jin, Sebastian Schmitt, Markus Olhofer
To this end, we develop a multi-objective Bayesian evolutionary optimization approach to HE-MOPs by exploiting the different data sets on the cheap and expensive objectives in HE-MOPs to alleviate the search bias caused by the heterogeneous evaluation costs for evaluating different objectives.
no code implementations • 9 Jun 2022 • Felix Lanfermann, Sebastian Schmitt
In this work, an approach to define meaningful and consistent concepts in an existing engineering dataset is presented.
no code implementations • 7 Jun 2022 • Xilu Wang, Yaochu Jin, Sebastian Schmitt, Markus Olhofer
Bayesian optimization has emerged at the forefront of expensive black-box optimization due to its data efficiency.
1 code implementation • 14 Apr 2022 • Andrea Castellani, Sebastian Schmitt, Barbara Hammer
Furthermore, we propose a drift-dependent dynamic budget strategy, which uses a variable distribution of the labelling budget over time, after a detected drift.
no code implementations • 21 Mar 2022 • Eric Müller, Elias Arnold, Oliver Breitwieser, Milena Czierlinski, Arne Emmel, Jakob Kaiser, Christian Mauch, Sebastian Schmitt, Philipp Spilger, Raphael Stock, Yannik Stradmann, Johannes Weis, Andreas Baumbach, Sebastian Billaudelle, Benjamin Cramer, Falk Ebert, Julian Göltz, Joscha Ilmberger, Vitali Karasenko, Mitja Kleider, Aron Leibfried, Christian Pehle, Johannes Schemmel
Neuromorphic systems open up opportunities to enlarge the explorative space for computational research.
no code implementations • 10 Dec 2021 • Patricia Wollstadt, Sebastian Schmitt
We thus demonstrate the power of novel information-theoretic approaches in identifying relevant parameters in optimization runs and highlight how these methods avoid the selection of redundant parameters, while detecting interactions that result in synergistic contributions of multiple parameters.
no code implementations • 30 Aug 2021 • Xilu Wang, Yaochu Jin, Sebastian Schmitt, Markus Olhofer
Most existing multiobjetive evolutionary algorithms (MOEAs) implicitly assume that each objective function can be evaluated within the same period of time.
1 code implementation • 16 Aug 2021 • Andrea Castellani, Sebastian Schmitt, Barbara Hammer
In the proposed framework, the actual method to detect a change in the statistics of incoming data samples can be chosen freely.
no code implementations • 10 May 2021 • Patricia Wollstadt, Sebastian Schmitt, Michael Wibral
We argue that this lack is inherent to classical information theory which does not provide measures to decompose the information a set of variables provides about a target into unique, redundant, and synergistic contributions.
1 code implementation • 1 May 2021 • Andrea Castellani, Sebastian Schmitt, Barbara Hammer
However, sensor failures result in mislabeled training data samples which are hard to detect and remove from the dataset.
no code implementations • 11 Mar 2021 • Theodoros Georgiou, Sebastian Schmitt, Thomas Bäck, Nan Pu, Wei Chen, Michael Lew
The output of such simulations, in particular the calculated flow fields, are usually very complex and hard to interpret for realistic three-dimensional real-world applications, especially if time-dependent simulations are investigated.
no code implementations • 11 Mar 2021 • Theodoros Georgiou, Sebastian Schmitt, Thomas Bäck, Wei Chen, Michael Lew
In this work we propose a weight soft-regularization method based on the Oblique manifold.
no code implementations • 12 Nov 2020 • Andrea Castellani, Sebastian Schmitt, Stefano Squartini
The approaches make use of a Digital Twin to generate a training dataset which simulates the normal operation of the machinery, along with a small set of labeled anomalous measurement from the real machinery.
no code implementations • 23 Jun 2020 • Philipp Spilger, Eric Müller, Arne Emmel, Aron Leibfried, Christian Mauch, Christian Pehle, Johannes Weis, Oliver Breitwieser, Sebastian Billaudelle, Sebastian Schmitt, Timo C. Wunderlich, Yannik Stradmann, Johannes Schemmel
We present software facilitating the usage of the BrainScaleS-2 analog neuromorphic hardware system as an inference accelerator for artificial neural networks.
no code implementations • 30 Mar 2020 • Eric Müller, Sebastian Schmitt, Christian Mauch, Sebastian Billaudelle, Andreas Grübl, Maurice Güttler, Dan Husmann, Joscha Ilmberger, Sebastian Jeltsch, Jakob Kaiser, Johann Klähn, Mitja Kleider, Christoph Koke, José Montes, Paul Müller, Johannes Partzsch, Felix Passenberg, Hartmut Schmidt, Bernhard Vogginger, Jonas Weidner, Christian Mayr, Johannes Schemmel
We present operation and development methodologies implemented for the BrainScaleS-1 neuromorphic architecture and walk through the individual components of BrainScaleS OS constituting the software stack for BrainScaleS-1 platform operation.
no code implementations • 16 Oct 2019 • Jakub Kmec, Sebastian Schmitt
The choices to be made in the setup of the optimization process strongly influence this mapping and thus are expected to have a profound influence on the achievable result.
no code implementations • 6 Jul 2018 • Akos F. Kungl, Sebastian Schmitt, Johann Klähn, Paul Müller, Andreas Baumbach, Dominik Dold, Alexander Kugele, Nico Gürtler, Luziwei Leng, Eric Müller, Christoph Koke, Mitja Kleider, Christian Mauch, Oliver Breitwieser, Maurice Güttler, Dan Husmann, Kai Husmann, Joscha Ilmberger, Andreas Hartel, Vitali Karasenko, Andreas Grübl, Johannes Schemmel, Karlheinz Meier, Mihai A. Petrovici
The massively parallel nature of biological information processing plays an important role for its superiority to human-engineered computing devices.
no code implementations • 17 Mar 2017 • Mihai A. Petrovici, Sebastian Schmitt, Johann Klähn, David Stöckel, Anna Schroeder, Guillaume Bellec, Johannes Bill, Oliver Breitwieser, Ilja Bytschok, Andreas Grübl, Maurice Güttler, Andreas Hartel, Stephan Hartmann, Dan Husmann, Kai Husmann, Sebastian Jeltsch, Vitali Karasenko, Mitja Kleider, Christoph Koke, Alexander Kononov, Christian Mauch, Eric Müller, Paul Müller, Johannes Partzsch, Thomas Pfeil, Stefan Schiefer, Stefan Scholze, Anand Subramoney, Vasilis Thanasoulis, Bernhard Vogginger, Robert Legenstein, Wolfgang Maass, René Schüffny, Christian Mayr, Johannes Schemmel, Karlheinz Meier
Despite being originally inspired by the central nervous system, artificial neural networks have diverged from their biological archetypes as they have been remodeled to fit particular tasks.
1 code implementation • 6 Mar 2017 • Sebastian Schmitt, Johann Klaehn, Guillaume Bellec, Andreas Gruebl, Maurice Guettler, Andreas Hartel, Stephan Hartmann, Dan Husmann, Kai Husmann, Vitali Karasenko, Mitja Kleider, Christoph Koke, Christian Mauch, Eric Mueller, Paul Mueller, Johannes Partzsch, Mihai A. Petrovici, Stefan Schiefer, Stefan Scholze, Bernhard Vogginger, Robert Legenstein, Wolfgang Maass, Christian Mayr, Johannes Schemmel, Karlheinz Meier
In this paper, we demonstrate how iterative training of a hardware-emulated network can compensate for anomalies induced by the analog substrate.