Zobrazeno 1 - 10
of 38 718
pro vyhledávání: '"Gottschalk A"'
Deep neural networks have achieved remarkable success in diverse applications, prompting the need for a solid theoretical foundation. Recent research has identified the minimal width $\max\{2,d_x,d_y\}$ required for neural networks with input dimensi
Externí odkaz:
http://arxiv.org/abs/2411.08735
Autor:
Afzali, Amirabbas, Khodabandeh, Borna, Rasekh, Ali, JafariNodeh, Mahyar, kazemi, Sepehr, Gottschalk, Simon
Contrastive learning models have demonstrated impressive abilities to capture semantic similarities by aligning representations in the embedding space. However, their performance can be limited by the quality of the training data and its inherent bia
Externí odkaz:
http://arxiv.org/abs/2411.08923
Autor:
Sao, Ashutosh, Gottschalk, Simon
Publikováno v:
27th European Conference on Artificial Intelligence (ECAI) 2024
Accurate spatio-temporal prediction is crucial for the sustainable development of smart cities. However, current approaches often struggle to capture important spatio-temporal relationships, particularly overlooking global relations among distant cit
Externí odkaz:
http://arxiv.org/abs/2411.06836
Developing a foundation model for time series forecasting across diverse domains has attracted significant attention in recent years. Existing works typically assume regularly sampled, well-structured data, limiting their applicability to more genera
Externí odkaz:
http://arxiv.org/abs/2410.23160
In recent years, a body of works has emerged, studying shape and texture biases of off-the-shelf pre-trained deep neural networks (DNN) for image classification. These works study how much a trained DNN relies on image cues, predominantly shape and t
Externí odkaz:
http://arxiv.org/abs/2410.14878
Autor:
Gottschalk, Jonas, Stellmer, Simon
Experiments in the field of quantum optics often require very low concentrations of dust particles in the laboratory, but the complexity of working routines precludes operation within a proper clean room. Research teams have established a multitude o
Externí odkaz:
http://arxiv.org/abs/2409.18325
Semantic segmentation networks have achieved significant success under the assumption of independent and identically distributed data. However, these networks often struggle to detect anomalies from unknown semantic classes due to the limited set of
Externí odkaz:
http://arxiv.org/abs/2409.17330
Autor:
Hon, Marc, Huber, Daniel, Li, Yaguang, Metcalfe, Travis S., Bedding, Timothy R., Ong, Joel, Chontos, Ashley, Rubenzahl, Ryan, Halverson, Samuel, García, Rafael A., Kjeldsen, Hans, Stello, Dennis, Hey, Daniel R., Campante, Tiago, Howard, Andrew W., Gibson, Steven R., Rider, Kodi, Roy, Arpita, Baker, Ashley D., Edelstein, Jerry, Smith, Chris, Fulton, Benjamin J., Walawender, Josh, Brodheim, Max, Brown, Matt, Chan, Dwight, Dai, Fei, Deich, William, Gottschalk, Colby, Grillo, Jason, Hale, Dave, Hill, Grant M., Holden, Bradford, Householder, Aaron, Isaacson, Howard, Ishikawa, Yuzo, Jelinsky, Sharon R., Kassis, Marc, Kaye, Stephen, Laher, Russ, Lanclos, Kyle, Lee, Chien-Hsiu, Lilley, Scott, McCarney, Ben, Miller, Timothy N., Payne, Joel, Petigura, Erik A., Poppett, Claire, Raffanti, Michael, Rockosi, Constance, Sanford, Dale, Schwab, Christian, Shaum, Abby P., Sirk, Martin M., Smith, Roger, Thorne, Jim, Valliant, John, Vandenberg, Adam, Wang, Shin Ywan, Wishnow, Edward, Wold, Truman, Yeh, Sherry, Baker, Ashley, Basu, Sarbani, Bedell, Megan, Cegla, Heather M., Crossfield, Ian, Dressing, Courtney, Dumusque, Xavier, Knutson, Heather, Mawet, Dimitri, O'Meara, John, Stefánsson, Guðmundur, Teske, Johanna, Vasisht, Gautam, Wang, Sharon Xuesong, Weiss, Lauren M., Winn, Joshua N., Wright, Jason T.
Asteroseismology of dwarf stars cooler than the Sun is very challenging due to the low amplitudes and rapid timescales of oscillations. Here, we present the asteroseismic detection of solar-like oscillations at 4-minute timescales ($\nu_{\mathrm{max}
Externí odkaz:
http://arxiv.org/abs/2407.21234
This paper focuses on hyperparameter optimization for autonomous driving strategies based on Reinforcement Learning. We provide a detailed description of training the RL agent in a simulation environment. Subsequently, we employ Efficient Global Opti
Externí odkaz:
http://arxiv.org/abs/2407.14262
In human interaction, gestures serve various functions such as marking speech rhythm, highlighting key elements, and supplementing information. These gestures are also observed in explanatory contexts. However, the impact of gestures on explanations
Externí odkaz:
http://arxiv.org/abs/2406.12544