| 1. |
- Gerken, Jan, 1991, et al.
(författare)
-
Equivariance versus augmentation for spherical images
- 2022
-
Ingår i: Proceedings of Machine Learning Resaerch. ; , s. 7404-7421
-
Konferensbidrag (refereegranskat)abstract
- We analyze the role of rotational equivariance in convolutional neural networks (CNNs) applied to spherical images. We compare the performance of the group equivariant networks known as S2CNNs and standard non-equivariant CNNs trained with an increasing amount of data augmentation. The chosen architectures can be considered baseline references for the respective design paradigms. Our models are trained and evaluated on single or multiple items from the MNIST- or FashionMNIST dataset projected onto the sphere. For the task of image classification, which is inherently rotationally invariant, we find that by considerably increasing the amount of data augmentation and the size of the networks, it is possible for the standard CNNs to reach at least the same performance as the equivariant network. In contrast, for the inherently equivariant task of semantic segmentation, the non-equivariant networks are consistently outperformed by the equivariant networks with significantly fewer parameters. We also analyze and compare the inference latency and training times of the different networks, enabling detailed tradeoff considerations between equivariant architectures and data augmentation for practical problems.
|
|
| 2. |
- Gerken, Jan, 1991, et al.
(författare)
-
Geometric deep learning and equivariant neural networks
- 2023
-
Ingår i: Artificial Intelligence Review. - : Springer Nature. - 1573-7462 .- 0269-2821. ; 56:12, s. 14605-14662
-
Tidskriftsartikel (refereegranskat)abstract
- We survey the mathematical foundations of geometric deep learning, focusing on group equivariant and gauge equivariant neural networks. We develop gauge equivariant convolutional neural networks on arbitrary manifolds M using principal bundles with structure group K and equivariant maps between sections of associated vector bundles. We also discuss group equivariant neural networks for homogeneous spaces M= G/ K , which are instead equivariant with respect to the global symmetry G on M . Group equivariant layers can be interpreted as intertwiners between induced representations of G, and we show their relation to gauge equivariant convolutional layers. We analyze several applications of this formalism, including semantic segmentation and object detection networks. We also discuss the case of spherical networks in great detail, corresponding to the case M= S2= SO (3) / SO (2) . Here we emphasize the use of Fourier analysis involving Wigner matrices, spherical harmonics and Clebsch–Gordan coefficients for G= SO (3) , illustrating the power of representation theory for deep learning.
|
|
| 3. |
- Nambiar, Sanjay, 1997-
(författare)
-
Adaptive Automation for Customized Products
- 2024
-
Licentiatavhandling (övrigt vetenskapligt/konstnärligt)abstract
- In today’s fast-paced industrial landscape, the drive for greater efficiency and flexibility in product development has sparked significant interest in innovative automation technologies. This thesis explores the usefulness of various automation techniques for customized products such as Knowledge-Based Engineering (KBE), Multidisciplinary Optimization (MDO) and machine learning frameworks.The research begins by establishing an automated framework for fixture design, combining design automation and MDO to streamline the design process. It then moves to optimizing gas turbines, introducing an automation framework that merges CAD templates with KBE principles.For complex and unstructured production, this thesis explores the use of Reinforcement Learning (RL) to tackle challenges in unstructured manufacturing. By utilizing lightweight physics-based engines and RL, the research advances automated assembly validation and mobile robot operations, pushing the boundaries of adaptive production automation. Furthermore, a framework is developed, which integrates smoothly with industrial robotic platforms showcases practical automation solutions and highlights the adaptability and applicability of digital twin technology in real-world situations.This thesis contributes to the field of product development by providing innovative solutions that are rooted in multidisciplinary research. It bridges the theoretical and practical aspects of automation with solutions that overcomes the obstacles to realize seamless integration between digital and physical realities in a manufacturing context.
|
|
