Zobrazeno 1 - 10
of 141
pro vyhledávání: '"Grewe, Benjamin F"'
Continual learning is the problem of integrating new information in a model while retaining the knowledge acquired in the past. Despite the tangible improvements achieved in recent years, the problem of continual learning is still an open one. A bett
Externí odkaz:
http://arxiv.org/abs/2407.16611
Autor:
Sager, Pascal J., Deriu, Jan M., Grewe, Benjamin F., Stadelmann, Thilo, von der Malsburg, Christoph
We present a novel intelligent-system architecture called "Dynamic Net Architecture" (DNA) that relies on recurrence-stabilized networks and discuss it in application to vision. Our architecture models a (cerebral cortical) area wherein elementary fe
Externí odkaz:
http://arxiv.org/abs/2407.05650
Deep learning has proved to be a successful paradigm for solving many challenges in machine learning. However, deep neural networks fail when trained sequentially on multiple tasks, a shortcoming known as catastrophic forgetting in the continual lear
Externí odkaz:
http://arxiv.org/abs/2310.01165
Autor:
Yan, Peng, Abdulkadir, Ahmed, Luley, Paul-Philipp, Rosenthal, Matthias, Schatte, Gerrit A., Grewe, Benjamin F., Stadelmann, Thilo
Publikováno v:
IEEE Acess 12 (2024) 3768-3789
Automating the monitoring of industrial processes has the potential to enhance efficiency and optimize quality by promptly detecting abnormal events and thus facilitating timely interventions. Deep learning, with its capacity to discern non-trivial p
Externí odkaz:
http://arxiv.org/abs/2307.05638
Autor:
Ao, Yunke, Esfandiari, Hooman, Carrillo, Fabio, As, Yarden, Farshad, Mazda, Grewe, Benjamin F., Krause, Andreas, Fuernstahl, Philipp
Spinal fusion surgery requires highly accurate implantation of pedicle screw implants, which must be conducted in critical proximity to vital structures with a limited view of anatomy. Robotic surgery systems have been proposed to improve placement a
Externí odkaz:
http://arxiv.org/abs/2305.05354
The ability to sequentially learn multiple tasks without forgetting is a key skill of biological brains, whereas it represents a major challenge to the field of deep learning. To avoid catastrophic forgetting, various continual learning (CL) approach
Externí odkaz:
http://arxiv.org/abs/2212.04316
We introduce meta-learning algorithms that perform zero-shot weight-space adaptation of neural network models to unseen tasks. Our methods repurpose the popular generative image synthesis techniques of natural language guidance and diffusion models t
Externí odkaz:
http://arxiv.org/abs/2210.08942
How can agents learn internal models that veridically represent interactions with the real world is a largely open question. As machine learning is moving towards representations containing not just observational but also interventional knowledge, we
Externí odkaz:
http://arxiv.org/abs/2207.12067
Introduction: In contrast to current AI technology, natural intelligence -- the kind of autonomous intelligence that is realized in the brains of animals and humans to attain in their natural environment goals defined by a repertoire of innate behavi
Externí odkaz:
http://arxiv.org/abs/2205.00002
Autor:
Meulemans, Alexander, Farinha, Matilde Tristany, Cervera, Maria R., Sacramento, João, Grewe, Benjamin F.
The success of deep learning ignited interest in whether the brain learns hierarchical representations using gradient-based learning. However, current biologically plausible methods for gradient-based credit assignment in deep neural networks need in
Externí odkaz:
http://arxiv.org/abs/2204.07249