Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Lengerich, Ben"'
Recent years have seen important advances in the building of interpretable models, machine learning models that are designed to be easily understood by humans. In this work, we show that large language models (LLMs) are remarkably good at working wit
Externí odkaz:
http://arxiv.org/abs/2402.14474
Autor:
Lengerich, Chris, Lengerich, Ben
We develop the few-shot continual learning task from first principles and hypothesize an evolutionary motivation and mechanism of action for executive function as a contrastive value policy which resamples and relabels perception data via hindsight s
Externí odkaz:
http://arxiv.org/abs/2204.12639
Context-specific Bayesian networks (i.e. directed acyclic graphs, DAGs) identify context-dependent relationships between variables, but the non-convexity induced by the acyclicity requirement makes it difficult to share information between context-sp
Externí odkaz:
http://arxiv.org/abs/2111.01104
Generalized additive models (GAMs) have become a leading modelclass for interpretable machine learning. However, there are many algorithms for training GAMs, and these can learn different or even contradictory models, while being equally accurate. Wh
Externí odkaz:
http://arxiv.org/abs/2006.06466
Autor:
Agarwal, Rishabh, Melnick, Levi, Frosst, Nicholas, Zhang, Xuezhou, Lengerich, Ben, Caruana, Rich, Hinton, Geoffrey
Deep neural networks (DNNs) are powerful black-box predictors that have achieved impressive performance on a wide variety of tasks. However, their accuracy comes at the cost of intelligibility: it is usually unclear how they make their decisions. Thi
Externí odkaz:
http://arxiv.org/abs/2004.13912
Autor:
Hegselmann, Stefan, Zhou, Helen, Yuyin Zhou, Chien, Jennifer, Sujay Nagaraj, Hulkund, Neha, Shreyas Bhave, Oberst, Michael, Amruta Pai, Ellington, Caleb, Wisdom Ikezogwo, Dou, Jason Xiaotian, Agrawal, Monica, Changye Li, Peniel Argaw, Biswas, Arpita, Mehak Gupta, Xinhui Li, Lemanczyk, Marta, Yuhui Zhang, Garbin, Christian, Healey, Elizabeth, Heejong Kim, Boone, Claire, Daneshjou, Roxana, Siyu Shi, Pezzotti, Nicola, Pfohl, Stephen R., Fong, Edwin, Aakanksha Naik, Lengerich, Ben, Xu, Ying, Bidwell, Jonathan, Sendak, Mark, Byung-Hak Kim, Hendrix, Nathaniel, Spathis, Dimitris, Seita, Jun, Quast, Bastiaan, Coffee, Megan, Stultz, Collin, Chen, Irene Y., Shalmali Joshi, Girmaw Abebe Tadesse
The second Machine Learning for Health (ML4H) symposium was held both virtually and in-person on November 28, 2022, in New Orleans, Louisiana, USA (Parziale et al.,2022). The symposium included research roundtable sessions to foster discussions betwe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::969fe62f3f872d1ab553c72494874f7a
Autor:
Hrovatin K; Institute of Computational Biology, Helmholtz Zentrum München, Neuherberg, Germany.; TUM School of Life Sciences Weihenstephan, Technical University of Munich, Freising, Germany.; Computer Science and Artificial Intelligence Lab, Massachusetts Institute of Technology, Cambridge, MA.; Broad Institute of MIT and Harvard, Cambridge, MA., Moinfar AA; Institute of Computational Biology, Helmholtz Zentrum München, Neuherberg, Germany.; School of Computation, Information and Technology, Technical University of Munich, Garching, Germany., Zappia L; Institute of Computational Biology, Helmholtz Zentrum München, Neuherberg, Germany.; School of Computation, Information and Technology, Technical University of Munich, Garching, Germany., Lapuerta AT; Institute of Computational Biology, Helmholtz Zentrum München, Neuherberg, Germany.; School of Computation, Information and Technology, Technical University of Munich, Garching, Germany., Lengerich B; Computer Science and Artificial Intelligence Lab, Massachusetts Institute of Technology, Cambridge, MA.; Broad Institute of MIT and Harvard, Cambridge, MA., Kellis M; Computer Science and Artificial Intelligence Lab, Massachusetts Institute of Technology, Cambridge, MA.; Broad Institute of MIT and Harvard, Cambridge, MA., Theis FJ; Institute of Computational Biology, Helmholtz Zentrum München, Neuherberg, Germany.; TUM School of Life Sciences Weihenstephan, Technical University of Munich, Freising, Germany.; School of Computation, Information and Technology, Technical University of Munich, Garching, Germany.
Publikováno v:
BioRxiv : the preprint server for biology [bioRxiv] 2024 Feb 10. Date of Electronic Publication: 2024 Feb 10.
