134 citations · 142 across the 20 of their papers we have counts for
5 papers · 1 filter
Dynamic Sparsity: Challenging Common Sparsity Assumptions for Learning World Models in Robotic Reinforcement Learning Benchmarks
Muthukumar Pandaram, Jakob Hollenstein, David Drexel +3
The use of learned dynamics models, also known as world models, can improve the sample efficiency of reinforcement learning. Recent work suggests that the underlying causal graphs…
Auto-tuning of Deep Neural Networks by Conflicting Layer Removal
David Peer, Sebastian Stabinger, Antonio Rodriguez-Sanchez
Designing neural network architectures is a challenging task and knowing which specific layers of a model must be adapted to improve the performance is almost a mystery. In this pa…
Conflicting Bundles: Adapting Architectures Towards the Improved Training of Deep Neural Networks
David Peer, Sebastian Stabinger, Antonio Rodriguez-Sanchez
Designing neural network architectures is a challenging task and knowing which specific layers of a model must be adapted to improve the performance is almost a mystery. In this pa…
Limitation of capsule networks
David Peer, Sebastian Stabinger, Antonio Rodriguez-Sanchez
A recently proposed method in deep learning groups multiple neurons to capsules such that each capsule represents an object or part of an object. Routing algorithms route the outpu…
Increasing the adversarial robustness and explainability of capsule networks with -capsules
David Peer, Sebastian Stabinger, Antonio Rodriguez-Sanchez
In this paper we introduce a new inductive bias for capsule networks and call networks that use this prior -capsule networks. Our inductive bias that is inspired by TE neurons o…