Zobrazeno 1 - 10
of 14 842
pro vyhledávání: '"Brendel A"'
Autor:
Brady, Jack, von Kügelgen, Julius, Lachapelle, Sébastien, Buchholz, Simon, Kipf, Thomas, Brendel, Wieland
Learning disentangled representations of concepts and re-composing them in unseen ways is crucial for generalizing to out-of-domain situations. However, the underlying properties of concepts that enable such disentanglement and compositional generali
Externí odkaz:
http://arxiv.org/abs/2411.07784
Autor:
Reizinger, Patrik, Bizeul, Alice, Juhos, Attila, Vogt, Julia E., Balestriero, Randall, Brendel, Wieland, Klindt, David
Supervised learning has become a cornerstone of modern machine learning, yet a comprehensive theory explaining its effectiveness remains elusive. Empirical phenomena, such as neural analogy-making and the linear representation hypothesis, suggest tha
Externí odkaz:
http://arxiv.org/abs/2410.21869
Enhancing speech quality under adverse SNR conditions remains a significant challenge for discriminative deep neural network (DNN)-based approaches. In this work, we propose DisCoGAN, which is a time-frequency-domain generative adversarial network (G
Externí odkaz:
http://arxiv.org/abs/2410.13599
Autor:
Mayilvahanan, Prasanna, Zimmermann, Roland S., Wiedemer, Thaddäus, Rusak, Evgenia, Juhos, Attila, Bethge, Matthias, Brendel, Wieland
Out-of-Domain (OOD) generalization is the ability of a model trained on one or more domains to generalize to unseen domains. In the ImageNet era of computer vision, evaluation sets for measuring a model's OOD performance were designed to be strictly
Externí odkaz:
http://arxiv.org/abs/2410.08258
LLMs show remarkable emergent abilities, such as inferring concepts from presumably out-of-distribution prompts, known as in-context learning. Though this success is often attributed to the Transformer architecture, our systematic understanding is li
Externí odkaz:
http://arxiv.org/abs/2409.13728
Autor:
Alvarado III, Efrain, Bostow, Kate B., Patra, Kishore C., Jacobus, Cooper H., Baer-Way, Raphael A., Jennings, Connor F., Pichay, Neil R., deGraw, Asia A., Vidal, Edgar P., Chander, Vidhi, Altunin, Ivan A., Brendel, Victoria M., Ehrich, Kingsley E., Sunseri, James D., May, Michael B., Punjabi, Druv H., Gendreau-Distler, Eli A., Risin, Sophia, Brink, Thomas G., Zheng, WeiKang, Filippenko, Alexei V.
We study transits of several ``hot Jupiter'' systems - including WASP-12 b, WASP-43 b, WASP-103 b, HAT-P-23 b, KELT-16 b, WD 1856+534 b, and WTS-2 b - with the goal of detecting tidal orbital decay and extending the baselines of transit times. We fin
Externí odkaz:
http://arxiv.org/abs/2409.04660
In this study, we conduct a comparative analysis of deep learning-based noise reduction methods in low signal-to-noise ratio (SNR) scenarios. Our investigation primarily focuses on five key aspects: The impact of training data, the influence of vario
Externí odkaz:
http://arxiv.org/abs/2408.14582
We present a method for blind acoustic parameter estimation from single-channel reverberant speech. The method is structured into three stages. In the first stage, a variational auto-encoder is trained to extract latent representations of acoustic im
Externí odkaz:
http://arxiv.org/abs/2407.19989
Autor:
Khan, Aafaque R., Hamden, Erika, Chung, Haeun, Choi, Heejoo, Kim, Daewook, Melso, Nicole, Hoadley, Keri, Vargas, Carlos J., Truong, Daniel, Garcia, Elijah, Verts, Bill, Coronado, Fernando, Noenickx, Jamison, Corliss, Jason, Tanquary, Hannah, Mcmahon, Tom, Hamara, Dave, Agarwal, Simran, Augustin, Ramona, Behroozi, Peter, Bradley, Harrison, Brendel, Trenton, Burchett, Joe, Castillo, Jasmine Martinez, Chambers, Jacob, Corlies, Lauren, Davis, Greyson, Dettmar, Ralf-Jürgen, Douglas, Ewan, Ghidoli, Giulia, Goodwin, Alfred, Harris, Walter, Hergenrother, Carl, Howk, J. Christopher, Keppler, Miriam, Kerkeser, Nazende Ipek, Kidd Jr., John N., Li, Jessica S., Noriega, Gabe, Park, Sooseong, Pecha, Ryan, Sauve, Cork, Schiminovich, David, Selznick, Sanford, Siegmund, Oswald, Su, Rebecca, Uppnor, Sumedha, Vider, Jacob, Wolcott, Ellie, Yescas, Naomi, Zaritsky, Dennis
Aspera is a NASA Astrophysics Pioneers SmallSat mission designed to study diffuse OVI emission from the warm-hot phase gas in the halos of nearby galaxies. Its payload consists of two identical Rowland Circle-type long-slit spectrographs, sharing a s
Externí odkaz:
http://arxiv.org/abs/2407.15391
Autor:
Rusak, Evgenia, Reizinger, Patrik, Juhos, Attila, Bringmann, Oliver, Zimmermann, Roland S., Brendel, Wieland
Previous theoretical work on contrastive learning (CL) with InfoNCE showed that, under certain assumptions, the learned representations uncover the ground-truth latent factors. We argue these theories overlook crucial aspects of how CL is deployed in
Externí odkaz:
http://arxiv.org/abs/2407.00143