79 citations · 370 across the 33 of their papers we have counts for
5 papers · 1 filter
TopicBERT for Energy Efficient Document Classification
Yatin Chaudhary, Pankaj Gupta, Khushbu Saxena +3
Prior research notes that BERT's computational cost grows quadratically with sequence length thus leading to longer training times, higher GPU memory constraints and carbon emissio…
Overcoming Model Bias for Robust Offline Deep Reinforcement Learning
Phillip Swazinna, Steffen Udluft, Thomas Runkler
State-of-the-art reinforcement learning algorithms mostly rely on being allowed to directly interact with their environment to collect millions of observations. This makes it hard…
Interpretable Control by Reinforcement Learning
Daniel Hein, Steffen Limmer, Thomas A. Runkler
In this paper, three recently introduced reinforcement learning (RL) methods are used to generate human-interpretable policies for the cart-pole balancing benchmark. The novel RL m…
Neural Topic Modeling with Continual Lifelong Learning
Pankaj Gupta, Yatin Chaudhary, Thomas Runkler +1
Lifelong learning has recently attracted attention in building machine learning systems that continually accumulate and transfer knowledge to help future learning. Unsupervised top…
Modeling System Dynamics with Physics-Informed Neural Networks Based on Lagrangian Mechanics
Manuel A. Roehrl, Thomas A. Runkler, Veronika Brandtstetter +2
Identifying accurate dynamic models is required for the simulation and control of various technical systems. In many important real-world applications, however, the two main modeli…