Zobrazeno 1 - 10
of 248
pro vyhledávání: '"Sandin, Fredrik"'
The short-loading cycle is a repetitive task performed in high quantities, making it a great alternative for automation. In the short-loading cycle, an expert operator navigates towards a pile, fills the bucket with material, navigates to a dump truc
Externí odkaz:
http://arxiv.org/abs/2406.13366
Autor:
Aehle, Max, Arsini, Lorenzo, Barreiro, R. Belén, Belias, Anastasios, Bury, Florian, Cebrian, Susana, Demin, Alexander, Dickinson, Jennet, Donini, Julien, Dorigo, Tommaso, Doro, Michele, Gauger, Nicolas R., Giammanco, Andrea, Gray, Lindsey, González, Borja S., Kain, Verena, Kieseler, Jan, Kusch, Lisa, Liwicki, Marcus, Maier, Gernot, Nardi, Federico, Ratnikov, Fedor, Roussel, Ryan, de Austri, Roberto Ruiz, Sandin, Fredrik, Schenk, Michael, Scarpa, Bruno, Silva, Pedro, Strong, Giles C., Vischia, Pietro
In this article we examine recent developments in the research area concerning the creation of end-to-end models for the complete optimization of measuring instruments. The models we consider rely on differentiable programming methods and on the spec
Externí odkaz:
http://arxiv.org/abs/2310.05673
We replace the multiplication and sigmoid function of the conventional recurrent gate with addition and ReLU activation. This mechanism is designed to maintain long-term memory for sequence processing but at a reduced computational cost, thereby open
Externí odkaz:
http://arxiv.org/abs/2308.05629
The concept of image similarity is ambiguous, and images can be similar in one context and not in another. This ambiguity motivates the creation of metrics for specific contexts. This work explores the ability of deep perceptual similarity (DPS) metr
Externí odkaz:
http://arxiv.org/abs/2304.02265
Autor:
Pihlgren, Gustav Grund, Nikolaidou, Konstantina, Chhipa, Prakash Chandra, Abid, Nosheen, Saini, Rajkumar, Sandin, Fredrik, Liwicki, Marcus
In recent years, deep perceptual loss has been widely and successfully used to train machine learning models for many computer vision tasks, including image synthesis, segmentation, and autoencoding. Deep perceptual loss is a type of loss function fo
Externí odkaz:
http://arxiv.org/abs/2302.04032
Autor:
Nilsson, Mattias, Pina, Ton Juny, Khacef, Lyes, Liwicki, Foteini, Chicca, Elisabetta, Sandin, Fredrik
With the expansion of AI-powered virtual assistants, there is a need for low-power keyword spotting systems providing a "wake-up" mechanism for subsequent computationally expensive speech recognition. One promising approach is the use of neuromorphic
Externí odkaz:
http://arxiv.org/abs/2301.09962
Autor:
Nilsson, Mattias, Schelén, Olov, Lindgren, Anders, Bodin, Ulf, Paniagua, Cristina, Delsing, Jerker, Sandin, Fredrik
Publikováno v:
Frontiers in Neuroscience 17 (2023)
Increasing complexity and data-generation rates in cyber-physical systems and the industrial Internet of things are calling for a corresponding increase in AI capabilities at the resource-constrained edges of the Internet. Meanwhile, the resource req
Externí odkaz:
http://arxiv.org/abs/2210.11190
Measuring the similarity of images is a fundamental problem to computer vision for which no universal solution exists. While simple metrics such as the pixel-wise L2-norm have been shown to have significant flaws, they remain popular. One group of re
Externí odkaz:
http://arxiv.org/abs/2207.02512
In the process industry, condition monitoring systems with automated fault diagnosis methods assist human experts and thereby improve maintenance efficiency, process sustainability, and workplace safety. Improving the automated fault diagnosis method
Externí odkaz:
http://arxiv.org/abs/2112.07356
Mixed-signal neuromorphic processors with brain-like organization and device physics offer an ultra-low-power alternative to the unsustainable developments of conventional deep learning and computing. However, realizing the potential of such neuromor
Externí odkaz:
http://arxiv.org/abs/2106.05686