Search Results for author: Martin V. Butz

Found 25 papers, 8 papers with code

Loci-Segmented: Improving Scene Segmentation Learning

1 code implementation16 Oct 2023 Manuel Traub, Frederic Becker, Adrian Sauter, Sebastian Otte, Martin V. Butz

Current slot-oriented approaches for compositional scene segmentation from images and videos rely on provided background information or slot assignments.

Scene Segmentation Segmentation

Looping LOCI: Developing Object Permanence from Videos

no code implementations16 Oct 2023 Manuel Traub, Frederic Becker, Sebastian Otte, Martin V. Butz

Recent compositional scene representation learning models have become remarkably good in segmenting and tracking distinct objects within visual scenes.

Object Representation Learning

Advancing Parsimonious Deep Learning Weather Prediction using the HEALPix Mesh

no code implementations11 Sep 2023 Matthias Karlbauer, Nathaniel Cresswell-Clay, Raul A. Moreno, Dale R. Durran, Thorsten Kurth, Martin V. Butz

We present a parsimonious deep learning weather prediction model on the Hierarchical Equal Area isoLatitude Pixelization (HEALPix) to forecast seven atmospheric variables for arbitrarily long lead times on a global approximately 110 km mesh at 3h time resolution.

Intelligent problem-solving as integrated hierarchical reinforcement learning

no code implementations18 Aug 2022 Manfred Eppe, Christian Gumbsch, Matthias Kerzel, Phuong D. H. Nguyen, Martin V. Butz, Stefan Wermter

According to cognitive psychology and related disciplines, the development of complex problem-solving behaviour in biological agents depends on hierarchical cognitive mechanisms.

Hierarchical Reinforcement Learning reinforcement-learning +1

Binding Dancers Into Attractors

no code implementations1 Jun 2022 Franziska Kaltenberger, Sebastian Otte, Martin V. Butz

Our system flexibly binds the information of the rotating figure into the alternative attractors resolving the illusion's ambiguity and imagining the respective depth interpretation and the corresponding direction of rotation.

Inference of Affordances and Active Motor Control in Simulated Agents

no code implementations23 Feb 2022 Fedor Scholz, Christian Gumbsch, Sebastian Otte, Martin V. Butz

We show that our architecture, which is trained end-to-end to minimize an approximation of free energy, develops latent states that can be interpreted as affordance maps.

Zero-shot Generalization

Composing Partial Differential Equations with Physics-Aware Neural Networks

1 code implementation23 Nov 2021 Matthias Karlbauer, Timothy Praditia, Sebastian Otte, Sergey Oladyshkin, Wolfgang Nowak, Martin V. Butz

We introduce a compositional physics-aware FInite volume Neural Network (FINN) for learning spatiotemporal advection-diffusion processes.

Out-of-Distribution Generalization

Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domains

1 code implementation NeurIPS 2021 Christian Gumbsch, Martin V. Butz, Georg Martius

A common approach to prediction and planning in partially observable domains is to use recurrent neural networks (RNNs), which ideally develop and maintain a latent memory about hidden, task-relevant factors.

Inductive Bias

Compositionality as Learning Bias in Generative RNNs solves the Omniglot Challenge

no code implementations ICLR Workshop Learning_to_Learn 2021 Sarah Fabi, Sebastian Otte, Martin V. Butz

One aspect of learning to learn concerns the development of compositional knowledge structures that can be flexibly recombined in a semantically meaningful manner to analogically solve related problems.

Hierarchical principles of embodied reinforcement learning: A review

no code implementations18 Dec 2020 Manfred Eppe, Christian Gumbsch, Matthias Kerzel, Phuong D. H. Nguyen, Martin V. Butz, Stefan Wermter

We then relate these insights with contemporary hierarchical reinforcement learning methods, and identify the key machine intelligence approaches that realise these mechanisms.

Hierarchical Reinforcement Learning reinforcement-learning +1

Binding and Perspective Taking as Inference in a Generative Neural Network Model

no code implementations9 Dec 2020 Mahdi Sadeghi, Fabian Schrodt, Sebastian Otte, Martin V. Butz

Evaluations show that the resulting gradient-based inference process solves the perspective taking and binding problem for known biological motion patterns, essentially yielding a Gestalt perception mechanism.

Active Tuning

no code implementations2 Oct 2020 Sebastian Otte, Matthias Karlbauer, Martin V. Butz

We introduce Active Tuning, a novel paradigm for optimizing the internal dynamics of recurrent neural networks (RNNs) on the fly.

Denoising Time Series +2

Latent State Inference in a Spatiotemporal Generative Model

no code implementations21 Sep 2020 Matthias Karlbauer, Tobias Menge, Sebastian Otte, Hendrik P. A. Lensch, Thomas Scholten, Volker Wulfmeyer, Martin V. Butz

Knowledge about the hidden factors that determine particular system dynamics is crucial for both explaining them and pursuing goal-directed interventions.

Causal Inference Time Series +1

Inferring, Predicting, and Denoising Causal Wave Dynamics

no code implementations19 Sep 2020 Matthias Karlbauer, Sebastian Otte, Hendrik P. A. Lensch, Thomas Scholten, Volker Wulfmeyer, Martin V. Butz

The novel DISTributed Artificial neural Network Architecture (DISTANA) is a generative, recurrent graph convolution neural network.

Denoising

Fostering Event Compression using Gated Surprise

no code implementations12 May 2020 Dania Humaidan, Sebastian Otte, Martin V. Butz

Here, we introduce a hierarchical, surprise-gated recurrent neural network architecture, which models this process and develops compact compressions of distinct event-like contexts.

Model-based Reinforcement Learning

Learning Precise Spike Timings with Eligibility Traces

no code implementations8 May 2020 Manuel Traub, Martin V. Butz, R. Harald Baayen, Sebastian Otte

As a consequence, this limits in principle the inherent advantage of SNNs, that is, the potential to develop codes that rely on precise relative spike timings.

Investigating Efficient Learning and Compositionality in Generative LSTM Networks

no code implementations16 Apr 2020 Sarah Fabi, Sebastian Otte, Jonas Gregor Wiese, Martin V. Butz

In the past, the character challenge was only met by complex algorithms that were provided with stochastic primitives.

Autonomous Identification and Goal-Directed Invocation of Event-Predictive Behavioral Primitives

no code implementations26 Feb 2019 Christian Gumbsch, Martin V. Butz, Georg Martius

Here, we introduce a computational learning architecture, termed surprise-based behavioral modularization into event-predictive structures (SUBMODES), that explores behavior and identifies the underlying behavioral units completely from scratch.

Learning, Planning, and Control in a Monolithic Neural Event Inference Architecture

2 code implementations19 Sep 2018 Martin V. Butz, David Bilkey, Dania Humaidan, Alistair Knott, Sebastian Otte

We introduce REPRISE, a REtrospective and PRospective Inference SchEme, which learns temporal event-predictive models of dynamical systems.

Model Predictive Control

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