Search Results for author: Michael Kopp

Found 16 papers, 13 papers with code

The impact of the AI revolution on asset management

no code implementations20 Apr 2023 Michael Kopp

Recent progress in deep learning, a special form of machine learning, has led to remarkable capabilities machines can now be endowed with: they can read and understand free flowing text, reason and bargain with human counterparts, translate texts between languages, learn how to take decisions to maximize certain outcomes, etc.

Asset Management

Metropolitan Segment Traffic Speeds from Massive Floating Car Data in 10 Cities

1 code implementation17 Feb 2023 Moritz Neun, Christian Eichenberger, Yanan Xin, Cheng Fu, Nina Wiedemann, Henry Martin, Martin Tomko, Lukas Ambühl, Luca Hermes, Michael Kopp

Traffic analysis is crucial for urban operations and planning, while the availability of dense urban traffic data beyond loop detectors is still scarce.

Privacy Preserving

Profiling and Improving the PyTorch Dataloader for high-latency Storage: A Technical Report

1 code implementation9 Nov 2022 Ivan Svogor, Christian Eichenberger, Markus Spanring, Moritz Neun, Michael Kopp

We designed a series of benchmarks that outline performance issues of certain steps in the data loading process.

Sketched Multi-view Subspace Learning for Hyperspectral Anomalous Change Detection

1 code implementation9 Oct 2022 Shizhen Chang, Michael Kopp, Pedram Ghamisi

In this paper, inspired by the sketched representation and multi-view subspace learning, a sketched multi-view subspace learning (SMSL) model is proposed for HSI anomalous change detection.

Change Detection

Txt2Img-MHN: Remote Sensing Image Generation from Text Using Modern Hopfield Networks

1 code implementation8 Aug 2022 Yonghao Xu, Weikang Yu, Pedram Ghamisi, Michael Kopp, Sepp Hochreiter

To better evaluate the realism and semantic consistency of the generated images, we further conduct zero-shot classification on real remote sensing data using the classification model trained on synthesized images.

Text-to-Image Generation Zero-Shot Learning

Landslide4Sense: Reference Benchmark Data and Deep Learning Models for Landslide Detection

no code implementations1 Jun 2022 Omid Ghorbanzadeh, Yonghao Xu, Pedram Ghamisi, Michael Kopp, David Kreil

We make the multi-source landslide benchmark data (Landslide4Sense) and the tested DL models publicly available at \url{https://www. iarai. ac. at/landslide4sense}, establishing an important resource for remote sensing, computer vision, and machine learning communities in studies of image classification in general and applications to landslide detection in particular.

Image Classification

A remark on a paper of Krotov and Hopfield [arXiv:2008.06996]

no code implementations31 May 2021 Fei Tang, Michael Kopp

In their recent paper titled "Large Associative Memory Problem in Neurobiology and Machine Learning" [arXiv:2008. 06996] the authors gave a biologically plausible microscopic theory from which one can recover many dense associative memory models discussed in the literature.

BIG-bench Machine Learning

Cross-Domain Few-Shot Learning by Representation Fusion

2 code implementations13 Oct 2020 Thomas Adler, Johannes Brandstetter, Michael Widrich, Andreas Mayr, David Kreil, Michael Kopp, Günter Klambauer, Sepp Hochreiter

On the few-shot datasets miniImagenet and tieredImagenet with small domain shifts, CHEF is competitive with state-of-the-art methods.

cross-domain few-shot learning Drug Discovery

Dark Matter properties through cosmic history

2 code implementations20 Apr 2020 Stéphane Ilić, Michael Kopp, Constantinos Skordis, Daniel B. Thomas

We perform the first test of dark matter (DM) stress-energy evolution through cosmic history, using cosmic microwave background measurements supplemented with baryon acoustic oscillation data and the Hubble Space Telescope key project data.

Cosmology and Nongalactic Astrophysics

An extensive investigation of the Generalised Dark Matter model

1 code implementation2 May 2016 Michael Kopp, Constantinos Skordis, Dan B. Thomas

We also consider other descriptions of imperfect fluids that have a non-perturbative definition and relate these to the GDM model.

Cosmology and Nongalactic Astrophysics General Relativity and Quantum Cosmology

Cannot find the paper you are looking for? You can Submit a new open access paper.