Zobrazeno 1 - 10
of 96
pro vyhledávání: '"Golkov, A."'
Post-training quantization is widely employed to reduce the computational demands of neural networks. Typically, individual substructures, such as layers or blocks of layers, are quantized with the objective of minimizing quantization errors in their
Externí odkaz:
http://arxiv.org/abs/2411.03934
Autor:
Bongratz, Fabian, Golkov, Vladimir, Mautner, Lukas, Della Libera, Luca, Heetmeyer, Frederik, Czaja, Felix, Rodemann, Julian, Cremers, Daniel
The field of reinforcement learning offers a large variety of concepts and methods to tackle sequential decision-making problems. This variety has become so large that choosing an algorithm for a task at hand can be challenging. In this work, we stre
Externí odkaz:
http://arxiv.org/abs/2407.20917
Autor:
Golkov, Roman, Shokef, Yair
Publikováno v:
European Physical Journal E 47, 14 (2024)
The organization of live cells into tissues and their subsequent biological function involves inter-cell mechanical interactions, which are mediated by their elastic environment. To model this interaction, we consider cells as spherical active force
Externí odkaz:
http://arxiv.org/abs/2309.09353
Autor:
Dang, Hoai Nam, Golkov, Vladimir, Wimmer, Thomas, Cremers, Daniel, Maier, Andreas, Zaiss, Moritz
Current MRI super-resolution (SR) methods only use existing contrasts acquired from typical clinical sequences as input for the neural network (NN). In turbo spin echo sequences (TSE) the sequence parameters can have a strong influence on the actual
Externí odkaz:
http://arxiv.org/abs/2305.07524
Autor:
Wimmer, Thomas, Golkov, Vladimir, Dang, Hoai Nam, Zaiss, Moritz, Maier, Andreas, Cremers, Daniel
The ability of convolutional neural networks (CNNs) to recognize objects regardless of their position in the image is due to the translation-equivariance of the convolutional operation. Group-equivariant CNNs transfer this equivariance to other trans
Externí odkaz:
http://arxiv.org/abs/2304.05864
We investigate the incorporation of visual relationships into the task of supervised image caption generation by proposing a model that leverages detected objects and auto-generated visual relationships to describe images in natural language. To do s
Externí odkaz:
http://arxiv.org/abs/2109.11398
Convolutional networks are successful, but they have recently been outperformed by new neural networks that are equivariant under rotations and translations. These new networks work better because they do not struggle with learning each possible orie
Externí odkaz:
http://arxiv.org/abs/2102.06942
Modern text-to-speech systems are able to produce natural and high-quality speech, but speech contains factors of variation (e.g. pitch, rhythm, loudness, timbre)\ that text alone cannot contain. In this work we move towards a speech synthesis system
Externí odkaz:
http://arxiv.org/abs/2010.15084
Autor:
Golkov, Vladimir, Becker, Alexander, Plop, Daniel T., Čuturilo, Daniel, Davoudi, Neda, Mendenhall, Jeffrey, Moretti, Rocco, Meiler, Jens, Cremers, Daniel
Computer-aided drug discovery is an essential component of modern drug development. Therein, deep learning has become an important tool for rapid screening of billions of molecules in silico for potential hits containing desired chemical features. De
Externí odkaz:
http://arxiv.org/abs/2007.07029
Convolutional networks are successful due to their equivariance/invariance under translations. However, rotatable data such as images, volumes, shapes, or point clouds require processing with equivariance/invariance under rotations in cases where the
Externí odkaz:
http://arxiv.org/abs/1910.14594