Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Christoph Feinauer"'
Publikováno v:
Machine Learning: Science and Technology, Vol 5, Iss 2, p 025061 (2024)
Recent works demonstrated the existence of a double-descent phenomenon for the generalization error of neural networks, where highly overparameterized models escape overfitting and achieve good test performance, at odds with the standard bias-varianc
Externí odkaz:
https://doaj.org/article/f44fc0f9e9fa4b1c850ebc3d61b7321d
Publikováno v:
PLoS Computational Biology, Vol 18, Iss 6, p e1010219 (2022)
Many different types of generative models for protein sequences have been proposed in literature. Their uses include the prediction of mutational effects, protein design and the prediction of structural properties. Neural network (NN) architectures h
Externí odkaz:
https://doaj.org/article/67a6f37fe7434783bd625513cda69ff4
Publikováno v:
PLoS ONE, Vol 11, Iss 2, p e0149166 (2016)
Interaction between proteins is a fundamental mechanism that underlies virtually all biological processes. Many important interactions are conserved across a large variety of species. The need to maintain interaction leads to a high degree of co-evol
Externí odkaz:
https://doaj.org/article/855b2040b1384f268b95586f581bedef
Publikováno v:
PLoS Computational Biology, Vol 10, Iss 10, p e1003847 (2014)
Correlation patterns in multiple sequence alignments of homologous proteins can be exploited to infer information on the three-dimensional structure of their members. The typical pipeline to address this task, which we in this paper refer to as the t
Externí odkaz:
https://doaj.org/article/218963cc1828459ea88ef83f9aaee8f5
Autor:
Carlo Baldassi, Marco Zamparo, Christoph Feinauer, Andrea Procaccini, Riccardo Zecchina, Martin Weigt, Andrea Pagnani
Publikováno v:
PLoS ONE, Vol 9, Iss 3, p e92721 (2014)
In the course of evolution, proteins show a remarkable conservation of their three-dimensional structure and their biological function, leading to strong evolutionary constraints on the sequence variability between homologous proteins. Our method aim
Externí odkaz:
https://doaj.org/article/d4d88aaa739445c99c721e30223b4003
Autor:
Christoph Feinauer, Emanuele Borgonovo
Generative models for protein sequences are important for protein design, mutational effect prediction and structure prediction. In all of these tasks, the introduction of models which include interactions between pairs of positions has had a major i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d99b9ae8e9b57206af15df3e2848cc68
https://doi.org/10.1101/2022.12.12.520028
https://doi.org/10.1101/2022.12.12.520028
Autor:
Barthelemy Meynard-Piganeau, Caterina Fabbri, Martin Weigt, Andrea Pagnani, Christoph Feinauer
MotivationBeing able to artificially design novel proteins of desired function is pivotal in many biological and biomedical applications. Generative statistical modeling has recently emerged as a new paradigm for designing amino acid sequences, inclu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a9da853ccb1164390fcaf0d3a8061296
https://doi.org/10.1101/2022.05.30.494026
https://doi.org/10.1101/2022.05.30.494026
Autor:
Fabrizio Pittorino, Antonio Ferraro, Gabriele Perugini, Christoph Feinauer, Carlo Baldassi, Riccardo Zecchina
We systematize the approach to the investigation of deep neural network landscapes by basing it on the geometry of the space of implemented functions rather than the space of parameters. Grouping classifiers into equivalence classes, we develop a sta
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7b9541cdc0ebb74aa0d272b70bd04d5f
Many different types of generative models for protein sequences have been proposed in literature. Their uses include the prediction of mutational effects, protein design and the prediction of structural properties. Neural network (NN) architectures h
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::74a95169eceb99774ef20363063c1e27
https://doi.org/10.1101/2021.10.14.464358
https://doi.org/10.1101/2021.10.14.464358
Autor:
Fabrizio Pittorino, Carlo Lucibello, Christoph Feinauer, Perugini, Gabriele, Carlo Baldassi, Demyanenko, Elizaveta, Zecchina, Riccardo
Publikováno v:
Università Commerciale Luigi Bocconi-IRIS
The properties of flat minima in the empirical risk landscape of neural networks have been debated for some time. Increasing evidence suggests they possess better generalization capabilities with respect to sharp ones. First, we discuss Gaussian mixt
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a348afa9aa03a52cad6b0e364808b7bb
http://arxiv.org/abs/2006.07897
http://arxiv.org/abs/2006.07897