no code implementations • 18 Mar 2024 • Johannes Pöppelbaum, Andreas Schwung
This time-series is processed using quaternion valued neural network layers, where we aim to preserve the relation between these features through the usage of the Hamilton product.
no code implementations • 23 Jan 2024 • Sofiene Lassoued, Andreas Schwung
PetriRL capitalizes on the inherent strengths of Petri nets in modelling discrete event systems while leveraging the advantages of a graph structure.
no code implementations • 31 Aug 2023 • Fernando Arévalo, Christian Alison M. Piolo, M. Tahasanul Ibrahim, Andreas Schwung
We propose a novel methodology to define assistance systems that rely on information fusion to combine different sources of information while providing an assessment.
no code implementations • 12 Apr 2023 • Marlon Löppenberg, Andreas Schwung
The digital transformation of automation places new demands on data acquisition and processing in industrial processes.
no code implementations • 26 Dec 2022 • Johannes Pöppelbaum, Andreas Schwung
Quaternion valued neural networks experienced rising popularity and interest from researchers in the last years, whereby the derivatives with respect to quaternions needed for optimization are calculated as the sum of the partial derivatives with respect to the real and imaginary parts.
no code implementations • 23 Dec 2022 • Fernando Arévalo, Tahasanul Ibrahim, Christian Alison M. Piolo, Andreas Schwung
We present an architecture for multi-class ensemble classification and an approach to quantify the uncertainty of the individual classifiers and the ensemble classifier.
no code implementations • 31 Aug 2022 • Maximilian Menke, Thomas Wenzel, Andreas Schwung
Object detection networks have reached an impressive performance level, yet a lack of suitable data in specific applications often limits it in practice.
no code implementations • 17 Nov 2020 • Johannes Pöppelbaum, Andreas Schwung
We propose a novel neural network architecture based on dual quaternions which allow for a compact representation of informations with a main focus on describing rigid body movements.
no code implementations • 17 Nov 2020 • Mohammed Sharafath Abdul Hameed, Md Muzahid Khan, Andreas Schwung
To this end, we apply a curiosity based reinforcement learning, using intrinsic motivation as a form of reward, on a flexible robot manufacturing cell to alleviate this problem.
no code implementations • 8 Sep 2020 • Mohammed Sharafath Abdul Hameed, Andreas Schwung
The proposed GraSP-RL outperforms the FIFO, TS, and GA for the trained task of planning 30 jobs in JSSP.
no code implementations • 25 May 2020 • Mohammed Sharafath Abdul Hameed, Gavneet Singh Chadha, Andreas Schwung, Steven X. Ding
The proposed method which we term as Gradient Monitoring(GM), is an approach to steer the learning in the weight parameters of a neural network based on the dynamic development and feedback from the training process itself.
1 code implementation • 1 Jul 2019 • Jan Niclas Reimann, Andreas Schwung
Compared to e. g. decision trees or bayesian classifiers, DNN suffer from bad interpretability where we understand by interpretability, that a human can easily derive the relations modeled by the network.
no code implementations • 29 May 2019 • Gavneet Singh Chadha, Andreas Schwung
The weights of this matrix then constitute the exponents of the corresponding components of the receptive field.
no code implementations • 8 May 2019 • Gavneet Singh Chadha, Jan Niclas Reimann, Andreas Schwung
One of the strengths of convolutional layers is the ability to learn features about spatial relations in the input domain using various parameterized convolutional kernels.