Search Results for author: Sepp Hochreiter

Found 62 papers, 44 papers with code

Geometry-Informed Neural Networks

no code implementations21 Feb 2024 Arturs Berzins, Andreas Radler, Sebastian Sanokowski, Sepp Hochreiter, Johannes Brandstetter

We introduce the concept of geometry-informed neural networks (GINNs), which encompass (i) learning under geometric constraints, (ii) neural fields as a suitable representation, and (iii) generating diverse solutions to under-determined systems often encountered in geometric tasks.

MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Representations

1 code implementation15 Feb 2024 Benedikt Alkin, Lukas Miklautz, Sepp Hochreiter, Johannes Brandstetter

The motivation behind MIM-Refiner is rooted in the insight that optimal representations within MIM models generally reside in intermediate layers.

Contrastive Learning Image Clustering +1

SymbolicAI: A framework for logic-based approaches combining generative models and solvers

2 code implementations1 Feb 2024 Marius-Constantin Dinu, Claudiu Leoveanu-Condrei, Markus Holzleitner, Werner Zellinger, Sepp Hochreiter

We conclude by introducing a quality measure and its empirical score for evaluating these computational graphs, and propose a benchmark that compares various state-of-the-art LLMs across a set of complex workflows.

Few-Shot Learning Probabilistic Programming

Variational Annealing on Graphs for Combinatorial Optimization

1 code implementation NeurIPS 2023 Sebastian Sanokowski, Wilhelm Berghammer, Sepp Hochreiter, Sebastian Lehner

Several recent unsupervised learning methods use probabilistic approaches to solve combinatorial optimization (CO) problems based on the assumption of statistically independent solution variables.

Combinatorial Optimization

Introducing an Improved Information-Theoretic Measure of Predictive Uncertainty

no code implementations14 Nov 2023 Kajetan Schweighofer, Lukas Aichberger, Mykyta Ielanskyi, Sepp Hochreiter

Our analyses show that the current measure erroneously assumes that the BMA predictive distribution is equivalent to the predictive distribution of the true model that generated the dataset.

Decision Making

Functional trustworthiness of AI systems by statistically valid testing

no code implementations4 Oct 2023 Bernhard Nessler, Thomas Doms, Sepp Hochreiter

The authors are concerned about the safety, health, and rights of the European citizens due to inadequate measures and procedures required by the current draft of the EU Artificial Intelligence (AI) Act for the conformity assessment of AI systems.

valid

Linear Alignment of Vision-language Models for Image Captioning

1 code implementation10 Jul 2023 Fabian Paischer, Markus Hofmarcher, Sepp Hochreiter, Thomas Adler

We propose a more efficient training protocol that fits a linear mapping between image and text embeddings of CLIP via a closed-form solution.

Image Captioning Language Modelling

Semantic HELM: A Human-Readable Memory for Reinforcement Learning

1 code implementation NeurIPS 2023 Fabian Paischer, Thomas Adler, Markus Hofmarcher, Sepp Hochreiter

Then we feed these tokens to a pretrained language model that serves the agent as memory and provides it with a coherent and human-readable representation of the past.

Dota 2 Language Modelling +3

Addressing Parameter Choice Issues in Unsupervised Domain Adaptation by Aggregation

1 code implementation2 May 2023 Marius-Constantin Dinu, Markus Holzleitner, Maximilian Beck, Hoan Duc Nguyen, Andrea Huber, Hamid Eghbal-zadeh, Bernhard A. Moser, Sergei Pereverzyev, Sepp Hochreiter, Werner Zellinger

Our method outperforms deep embedded validation (DEV) and importance weighted validation (IWV) on all datasets, setting a new state-of-the-art performance for solving parameter choice issues in unsupervised domain adaptation with theoretical error guarantees.

Unsupervised Domain Adaptation

Context-enriched molecule representations improve few-shot drug discovery

1 code implementation24 Apr 2023 Johannes Schimunek, Philipp Seidl, Lukas Friedrich, Daniel Kuhn, Friedrich Rippmann, Sepp Hochreiter, Günter Klambauer

Our novel concept for molecule representation enrichment is to associate molecules from both the support set and the query set with a large set of reference (context) molecules through a Modern Hopfield Network.

Drug Discovery Few-Shot Learning

Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget

1 code implementation20 Apr 2023 Johannes Lehner, Benedikt Alkin, Andreas Fürst, Elisabeth Rumetshofer, Lukas Miklautz, Sepp Hochreiter

In this work, we study how to combine the efficiency and scalability of MIM with the ability of ID to perform downstream classification in the absence of large amounts of labeled data.

 Ranked #1 on Image Clustering on Imagenet-dog-15 (using extra training data)

Clustering Contrastive Learning +2

Conformal Prediction for Time Series with Modern Hopfield Networks

1 code implementation NeurIPS 2023 Andreas Auer, Martin Gauch, Daniel Klotz, Sepp Hochreiter

To quantify uncertainty, conformal prediction methods are gaining continuously more interest and have already been successfully applied to various domains.

Conformal Prediction Time Series

Enhancing Activity Prediction Models in Drug Discovery with the Ability to Understand Human Language

1 code implementation6 Mar 2023 Philipp Seidl, Andreu Vall, Sepp Hochreiter, Günter Klambauer

Activity and property prediction models are the central workhorses in drug discovery and materials sciences, but currently they have to be trained or fine-tuned for new tasks.

Activity Prediction Attribute +3

G-Signatures: Global Graph Propagation With Randomized Signatures

no code implementations17 Feb 2023 Bernhard Schäfl, Lukas Gruber, Johannes Brandstetter, Sepp Hochreiter

Graph neural networks (GNNs) have evolved into one of the most popular deep learning architectures.

Graph Learning

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

Few-Shot Learning by Dimensionality Reduction in Gradient Space

1 code implementation7 Jun 2022 Martin Gauch, Maximilian Beck, Thomas Adler, Dmytro Kotsur, Stefan Fiel, Hamid Eghbal-zadeh, Johannes Brandstetter, Johannes Kofler, Markus Holzleitner, Werner Zellinger, Daniel Klotz, Sepp Hochreiter, Sebastian Lehner

We introduce SubGD, a novel few-shot learning method which is based on the recent finding that stochastic gradient descent updates tend to live in a low-dimensional parameter subspace.

Dimensionality Reduction Few-Shot Learning

Entangled Residual Mappings

no code implementations2 Jun 2022 Mathias Lechner, Ramin Hasani, Zahra Babaiee, Radu Grosu, Daniela Rus, Thomas A. Henzinger, Sepp Hochreiter

Residual mappings have been shown to perform representation learning in the first layers and iterative feature refinement in higher layers.

Inductive Bias Representation Learning

Hopular: Modern Hopfield Networks for Tabular Data

1 code implementation1 Jun 2022 Bernhard Schäfl, Lukas Gruber, Angela Bitto-Nemling, Sepp Hochreiter

In experiments on small-sized tabular datasets with less than 1, 000 samples, Hopular surpasses Gradient Boosting, Random Forests, SVMs, and in particular several Deep Learning methods.

General Classification

Boundary Graph Neural Networks for 3D Simulations

1 code implementation21 Jun 2021 Andreas Mayr, Sebastian Lehner, Arno Mayrhofer, Christoph Kloss, Sepp Hochreiter, Johannes Brandstetter

However, it is notoriously difficult to integrate them into machine learning approaches due to their heterogeneity with respect to size and orientation.

Computational Efficiency

Learning 3D Granular Flow Simulations

1 code implementation4 May 2021 Andreas Mayr, Sebastian Lehner, Arno Mayrhofer, Christoph Kloss, Sepp Hochreiter, Johannes Brandstetter

Recently, the application of machine learning models has gained momentum in natural sciences and engineering, which is a natural fit due to the abundance of data in these fields.

BIG-bench Machine Learning

Trusted Artificial Intelligence: Towards Certification of Machine Learning Applications

no code implementations31 Mar 2021 Philip Matthias Winter, Sebastian Eder, Johannes Weissenböck, Christoph Schwald, Thomas Doms, Tom Vogt, Sepp Hochreiter, Bernhard Nessler

Artificial Intelligence is one of the fastest growing technologies of the 21st century and accompanies us in our daily lives when interacting with technical applications.

BIG-bench Machine Learning Ethics

MC-LSTM: Mass-Conserving LSTM

1 code implementation13 Jan 2021 Pieter-Jan Hoedt, Frederik Kratzert, Daniel Klotz, Christina Halmich, Markus Holzleitner, Grey Nearing, Sepp Hochreiter, Günter Klambauer

MC-LSTMs set a new state-of-the-art for neural arithmetic units at learning arithmetic operations, such as addition tasks, which have a strong conservation law, as the sum is constant over time.

Inductive Bias

Uncertainty Estimation with Deep Learning for Rainfall-Runoff Modelling

no code implementations15 Dec 2020 Daniel Klotz, Frederik Kratzert, Martin Gauch, Alden Keefe Sampson, Günter Klambauer, Sepp Hochreiter, Grey Nearing

Deep Learning is becoming an increasingly important way to produce accurate hydrological predictions across a wide range of spatial and temporal scales.

Benchmarking

Convergence Proof for Actor-Critic Methods Applied to PPO and RUDDER

no code implementations2 Dec 2020 Markus Holzleitner, Lukas Gruber, José Arjona-Medina, Johannes Brandstetter, Sepp Hochreiter

We prove under commonly used assumptions the convergence of actor-critic reinforcement learning algorithms, which simultaneously learn a policy function, the actor, and a value function, the critic.

Reinforcement Learning (RL) valid

Rainfall-Runoff Prediction at Multiple Timescales with a Single Long Short-Term Memory Network

1 code implementation15 Oct 2020 Martin Gauch, Frederik Kratzert, Daniel Klotz, Grey Nearing, Jimmy Lin, Sepp Hochreiter

Compared to naive prediction with a distinct LSTM per timescale, the multi-timescale architectures are computationally more efficient with no loss in accuracy.

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

Detecting cutaneous basal cell carcinomas in ultra-high resolution and weakly labelled histopathological images

no code implementations14 Nov 2019 Susanne Kimeswenger, Elisabeth Rumetshofer, Markus Hofmarcher, Philipp Tschandl, Harald Kittler, Sepp Hochreiter, Wolfram Hötzenecker, Günter Klambauer

The aim of this study is to evaluate whether it is possible to detect basal cell carcinomas in histological sections using attention-based deep learning models and to overcome the ultra-high resolution and the weak labels of whole slide images.

whole slide images

Explaining and Interpreting LSTMs

no code implementations25 Sep 2019 Leila Arras, Jose A. Arjona-Medina, Michael Widrich, Grégoire Montavon, Michael Gillhofer, Klaus-Robert Müller, Sepp Hochreiter, Wojciech Samek

While neural networks have acted as a strong unifying force in the design of modern AI systems, the neural network architectures themselves remain highly heterogeneous due to the variety of tasks to be solved.

A GAN based solver of black-box inverse problems

no code implementations NeurIPS Workshop Deep_Invers 2019 Michael Gillhofer, Hubert Ramsauer, Johannes Brandstetter, Bernhard Schäfl, Sepp Hochreiter

We propose a GAN based approach to solve inverse problems which have non-differential or non-continuous forward relations.

Towards Learning Universal, Regional, and Local Hydrological Behaviors via Machine-Learning Applied to Large-Sample Datasets

1 code implementation19 Jul 2019 Frederik Kratzert, Daniel Klotz, Guy Shalev, Günter Klambauer, Sepp Hochreiter, Grey Nearing

The problem currently is that traditional hydrological models degrade significantly in performance when calibrated for multiple basins together instead of for a single basin alone.

Benchmarking BIG-bench Machine Learning +2

Human-level Protein Localization with Convolutional Neural Networks

1 code implementation ICLR 2019 Elisabeth Rumetshofer, Markus Hofmarcher, Clemens Röhrl, Sepp Hochreiter, Günter Klambauer

We present the largest comparison of CNN architectures including GapNet-PL for protein localization in HTI images of human cells.

NeuralHydrology -- Interpreting LSTMs in Hydrology

no code implementations19 Mar 2019 Frederik Kratzert, Mathew Herrnegger, Daniel Klotz, Sepp Hochreiter, Günter Klambauer

LSTMs are particularly well-suited for this problem since memory cells can represent dynamic reservoirs and storages, which are essential components in state-space modelling approaches of the hydrological system.

Interpretable Deep Learning in Drug Discovery

1 code implementation7 Mar 2019 Kristina Preuer, Günter Klambauer, Friedrich Rippmann, Sepp Hochreiter, Thomas Unterthiner

Without any means of interpretation, neural networks that predict molecular properties and bioactivities are merely black boxes.

Drug Discovery

Fréchet ChemNet Distance: A metric for generative models for molecules in drug discovery

2 code implementations26 Mar 2018 Kristina Preuer, Philipp Renz, Thomas Unterthiner, Sepp Hochreiter, Günter Klambauer

We propose a novel distance measure between two sets of molecules, called Fr\'echet ChemNet distance (FCD), that can be used as an evaluation metric for generative models.

Drug Discovery

First Order Generative Adversarial Networks

1 code implementation ICML 2018 Calvin Seward, Thomas Unterthiner, Urs Bergmann, Nikolay Jetchev, Sepp Hochreiter

To formally describe an optimal update direction, we introduce a theoretical framework which allows the derivation of requirements on both the divergence and corresponding method for determining an update direction, with these requirements guaranteeing unbiased mini-batch updates in the direction of steepest descent.

Image Generation Text Generation

DeepSynergy: Predicting Anti-Cancer Drug Synergy with Deep Learning

1 code implementation Bioinformatics 2017 Kristina Preuer, Richard P I Lewis, Sepp Hochreiter, Andreas Bender, Krishna C Bulusu, Günter Klambauer

While drug combination therapies are a well-established concept in cancer treatment, identifying novel synergistic combinations is challenging due to the size of combinatorial space.

Coulomb GANs: Provably Optimal Nash Equilibria via Potential Fields

1 code implementation ICLR 2018 Thomas Unterthiner, Bernhard Nessler, Calvin Seward, Günter Klambauer, Martin Heusel, Hubert Ramsauer, Sepp Hochreiter

We prove that Coulomb GANs possess only one Nash equilibrium which is optimal in the sense that the model distribution equals the target distribution.

Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)

16 code implementations23 Nov 2015 Djork-Arné Clevert, Thomas Unterthiner, Sepp Hochreiter

In contrast to ReLUs, ELUs have negative values which allows them to push mean unit activations closer to zero like batch normalization but with lower computational complexity.

Ranked #144 on Image Classification on CIFAR-100 (using extra training data)

General Classification Image Classification

Toxicity Prediction using Deep Learning

1 code implementation4 Mar 2015 Thomas Unterthiner, Andreas Mayr, Günter Klambauer, Sepp Hochreiter

The goal of this challenge was to assess the performance of computational methods in predicting the toxicity of chemical compounds.

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