93 citations · 150 across the 20 of their papers we have counts for
14 papers · 1 filter
Minimal Convolutional RNNs Accelerate Spatiotemporal Learning
Coşku Can Horuz, Sebastian Otte, Martin V. Butz +1
We introduce MinConvLSTM and MinConvGRU, two novel spatiotemporal models that combine the spatial inductive biases of convolutional recurrent networks with the training efficiency…
Developing hierarchical anticipations via neural network-based event segmentation
Christian Gumbsch, Maurits Adam, Birgit Elsner +2
Humans can make predictions on various time scales and hierarchical levels. Thereby, the learning of event encodings seems to play a crucial role. In this work we model the develop…
Composing Partial Differential Equations with Physics-Aware Neural Networks
Matthias Karlbauer, Timothy Praditia, Sebastian Otte +3
We introduce a compositional physics-aware FInite volume Neural Network (FINN) for learning spatiotemporal advection-diffusion processes. FINN implements a new way of combining the…
Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domains
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 hi…
Latent Event-Predictive Encodings through Counterfactual Regularization
Dania Humaidan, Sebastian Otte, Christian Gumbsch +2
A critical challenge for any intelligent system is to infer structure from continuous data streams. Theories of event-predictive cognition suggest that the brain segments sensorimo…
Finite Volume Neural Network: Modeling Subsurface Contaminant Transport
Timothy Praditia, Matthias Karlbauer, Sebastian Otte +3
Data-driven modeling of spatiotemporal physical processes with general deep learning methods is a highly challenging task. It is further exacerbated by the limited availability of…
Binding and Perspective Taking as Inference in a Generative Neural Network Model
Mahdi Sadeghi, Fabian Schrodt, Sebastian Otte +1
The ability to flexibly bind features into coherent wholes from different perspectives is a hallmark of cognition and intelligence. Importantly, the binding problem is not only rel…
Active Tuning
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. In contrast to the conventional sequence-to-sequen…
Inferring, Predicting, and Denoising Causal Wave Dynamics
Matthias Karlbauer, Sebastian Otte, Hendrik P. A. Lensch +3
The novel DISTributed Artificial neural Network Architecture (DISTANA) is a generative, recurrent graph convolution neural network. It implements a grid or mesh of locally paramete…
Latent State Inference in a Spatiotemporal Generative Model
Matthias Karlbauer, Tobias Menge, Sebastian Otte +4
Knowledge about the hidden factors that determine particular system dynamics is crucial for both explaining them and pursuing goal-directed interventions. Inferring these factors f…
Fostering Event Compression using Gated Surprise
Dania Humaidan, Sebastian Otte, Martin V. Butz
Our brain receives a dynamically changing stream of sensorimotor data. Yet, we perceive a rather organized world, which we segment into and perceive as events. Computational theori…
Investigating Efficient Learning and Compositionality in Generative LSTM Networks
Sarah Fabi, Sebastian Otte, Jonas Gregor Wiese +1
When comparing human with artificial intelligence, one major difference is apparent: Humans can generalize very broadly from sparse data sets because they are able to recombine and…
A Distributed Neural Network Architecture for Robust Non-Linear Spatio-Temporal Prediction
Matthias Karlbauer, Sebastian Otte, Hendrik P. A. Lensch +3
We introduce a distributed spatio-temporal artificial neural network architecture (DISTANA). It encodes mesh nodes using recurrent, neural prediction kernels (PKs), while neural tr…
Learning, Planning, and Control in a Monolithic Neural Event Inference Architecture
Martin V. Butz, David Bilkey, Dania Humaidan +2
We introduce REPRISE, a REtrospective and PRospective Inference SchEme, which learns temporal event-predictive models of dynamical systems. REPRISE infers the unobservable contextu…