Cover Image

Analyzing inverse problems with invertible neural networks

In many tasks, in particular in natural science, the goal is to determine hidden system parameters from a set of measurements. Often, the forward process from parameter- to measurement-space is a well-defined function, whereas the inverse problem is ambiguous: one measurement may map to multiple dif...

Full description

Saved in:
Bibliographic Details
Main Authors: Ardizzone, Lynton (Author) , Kruse, Jakob (Author) , Wirkert, Sebastian (Author) , Rahner, Daniel (Author) , Pellegrini, Eric William (Author) , Klessen, Ralf S. (Author) , Maier-Hein, Lena (Author) , Rother, Carsten (Author) , Köthe, Ullrich (Author)
Format: Article (Journal) Chapter/Article
Language:English
Published: 2018
In: Arxiv
Year: 2018, Pages: 1-20
DOI:10.48550/arXiv.1808.04730
Online Access:Verlag, lizenzpflichtig, Volltext: https://doi.org/10.48550/arXiv.1808.04730
Verlag, lizenzpflichtig, Volltext: http://arxiv.org/abs/1808.04730
Get full text
Author Notes:Lynton Ardizzone, Jakob Kruse, Sebastian Wirkert, Daniel Rahner, Eric W. Pellegrini, Ralf S. Klessen, Lena Maier-Hein, Carsten Rother, Ullrich Köthe

MARC

LEADER 00000caa a2200000 c 4500
001 1810855101
003 DE-627
005 20220820225350.0
007 cr uuu---uuuuu
008 220719s2018 xx |||||o 00| ||eng c
024 7 |a 10.48550/arXiv.1808.04730  |2 doi 
035 |a (DE-627)1810855101 
035 |a (DE-599)KXP1810855101 
035 |a (OCoLC)1341464117 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 29  |2 sdnb 
100 1 |a Ardizzone, Lynton  |d 1994-  |e VerfasserIn  |0 (DE-588)1194988512  |0 (DE-627)1677182296  |4 aut 
245 1 0 |a Analyzing inverse problems with invertible neural networks  |c Lynton Ardizzone, Jakob Kruse, Sebastian Wirkert, Daniel Rahner, Eric W. Pellegrini, Ralf S. Klessen, Lena Maier-Hein, Carsten Rother, Ullrich Köthe 
264 1 |c 2018 
300 |a 20 
336 |a Text  |b txt  |2 rdacontent 
337 |a Computermedien  |b c  |2 rdamedia 
338 |a Online-Ressource  |b cr  |2 rdacarrier 
500 |a Identifizierung der Ressource nach: 6 Feb 2019 
500 |a Gesehen am 26.07.2022 
520 |a In many tasks, in particular in natural science, the goal is to determine hidden system parameters from a set of measurements. Often, the forward process from parameter- to measurement-space is a well-defined function, whereas the inverse problem is ambiguous: one measurement may map to multiple different sets of parameters. In this setting, the posterior parameter distribution, conditioned on an input measurement, has to be determined. We argue that a particular class of neural networks is well suited for this task -- so-called Invertible Neural Networks (INNs). Although INNs are not new, they have, so far, received little attention in literature. While classical neural networks attempt to solve the ambiguous inverse problem directly, INNs are able to learn it jointly with the well-defined forward process, using additional latent output variables to capture the information otherwise lost. Given a specific measurement and sampled latent variables, the inverse pass of the INN provides a full distribution over parameter space. We verify experimentally, on artificial data and real-world problems from astrophysics and medicine, that INNs are a powerful analysis tool to find multi-modalities in parameter space, to uncover parameter correlations, and to identify unrecoverable parameters. 
650 4 |a 68T01 
650 4 |a Computer Science - Machine Learning 
650 4 |a Statistics - Machine Learning 
700 1 |a Kruse, Jakob  |d 1990-  |e VerfasserIn  |0 (DE-588)1194989497  |0 (DE-627)1677183136  |4 aut 
700 1 |a Wirkert, Sebastian  |e VerfasserIn  |0 (DE-588)116867221X  |0 (DE-627)1032442506  |0 (DE-576)511693540  |4 aut 
700 1 |a Rahner, Daniel  |d 1992-  |e VerfasserIn  |0 (DE-588)1169353606  |0 (DE-627)1033583863  |0 (DE-576)51207819X  |4 aut 
700 1 |a Pellegrini, Eric William  |e VerfasserIn  |0 (DE-588)1142258947  |0 (DE-627)1001431359  |0 (DE-576)494751932  |4 aut 
700 1 |a Klessen, Ralf S.  |d 1968-  |e VerfasserIn  |0 (DE-588)120533820  |0 (DE-627)392381532  |0 (DE-576)178685399  |4 aut 
700 1 |a Maier-Hein, Lena  |d 1980-  |e VerfasserIn  |0 (DE-588)1075029252  |0 (DE-627)832869899  |0 (DE-576)190090804  |4 aut 
700 1 |a Rother, Carsten  |e VerfasserIn  |0 (DE-588)1181464692  |0 (DE-627)1662676883  |4 aut 
700 1 |a Köthe, Ullrich  |e VerfasserIn  |0 (DE-588)123963435  |0 (DE-627)594480884  |0 (DE-576)304484520  |4 aut 
773 0 8 |i Enthalten in  |t Arxiv  |d Ithaca, NY : Cornell University, 1991  |g (2018), Artikel-ID 1808.04730, Seite 1-20  |h Online-Ressource  |w (DE-627)509006531  |w (DE-600)2225896-6  |w (DE-576)28130436X  |7 nnas  |a Analyzing inverse problems with invertible neural networks 
773 1 8 |g year:2018  |g elocationid:1808.04730  |g pages:1-20  |g extent:20  |a Analyzing inverse problems with invertible neural networks 
856 4 0 |u https://doi.org/10.48550/arXiv.1808.04730  |x Verlag  |x Resolving-System  |z lizenzpflichtig  |3 Volltext 
856 4 0 |u http://arxiv.org/abs/1808.04730  |x Verlag  |z lizenzpflichtig  |3 Volltext 
951 |a AR 
992 |a 20220719 
993 |a Article 
994 |a 2018 
998 |g 123963435  |a Köthe, Ullrich  |m 123963435:Köthe, Ullrich  |d 700000  |d 708070  |e 700000PK123963435  |e 708070PK123963435  |k 0/700000/  |k 1/700000/708070/  |p 9  |y j 
998 |g 1181464692  |a Rother, Carsten  |m 1181464692:Rother, Carsten  |d 700000  |d 708070  |e 700000PR1181464692  |e 708070PR1181464692  |k 0/700000/  |k 1/700000/708070/  |p 8 
998 |g 1075029252  |a Maier-Hein, Lena  |m 1075029252:Maier-Hein, Lena  |d 50000  |e 50000PM1075029252  |k 0/50000/  |p 7 
998 |g 120533820  |a Klessen, Ralf S.  |m 120533820:Klessen, Ralf S.  |d 700000  |d 714000  |d 714200  |e 700000PK120533820  |e 714000PK120533820  |e 714200PK120533820  |k 0/700000/  |k 1/700000/714000/  |k 2/700000/714000/714200/  |p 6 
998 |g 1142258947  |a Pellegrini, Eric William  |m 1142258947:Pellegrini, Eric William  |d 500000  |d 500881  |e 500000PP1142258947  |e 500881PP1142258947  |k 0/500000/  |k 1/500000/500881/  |p 5 
998 |g 1169353606  |a Rahner, Daniel  |m 1169353606:Rahner, Daniel  |d 500000  |d 500881  |e 500000PR1169353606  |e 500881PR1169353606  |k 0/500000/  |k 1/500000/500881/  |p 4 
998 |g 1194989497  |a Kruse, Jakob  |m 1194989497:Kruse, Jakob  |d 700000  |d 708070  |e 700000PK1194989497  |e 708070PK1194989497  |k 0/700000/  |k 1/700000/708070/  |p 2 
998 |g 1194988512  |a Ardizzone, Lynton  |m 1194988512:Ardizzone, Lynton  |d 110000  |e 110000PA1194988512  |k 0/110000/  |p 1  |x j 
999 |a KXP-PPN1810855101  |e 4170230876 
BIB |a Y 
JSO |a {"origin":[{"dateIssuedKey":"2018","dateIssuedDisp":"2018"}],"person":[{"given":"Lynton","role":"aut","family":"Ardizzone","display":"Ardizzone, Lynton"},{"display":"Kruse, Jakob","family":"Kruse","given":"Jakob","role":"aut"},{"display":"Wirkert, Sebastian","given":"Sebastian","role":"aut","family":"Wirkert"},{"role":"aut","given":"Daniel","family":"Rahner","display":"Rahner, Daniel"},{"family":"Pellegrini","role":"aut","given":"Eric William","display":"Pellegrini, Eric William"},{"display":"Klessen, Ralf S.","family":"Klessen","role":"aut","given":"Ralf S."},{"display":"Maier-Hein, Lena","family":"Maier-Hein","role":"aut","given":"Lena"},{"display":"Rother, Carsten","given":"Carsten","role":"aut","family":"Rother"},{"family":"Köthe","given":"Ullrich","role":"aut","display":"Köthe, Ullrich"}],"relHost":[{"physDesc":[{"extent":"Online-Ressource"}],"recId":"509006531","disp":"Analyzing inverse problems with invertible neural networksArxiv","origin":[{"publisher":"Cornell University ; Arxiv.org","publisherPlace":"Ithaca, NY ; [Erscheinungsort nicht ermittelbar]","dateIssuedDisp":"1991-","dateIssuedKey":"1991"}],"note":["Gesehen am 28.05.2024"],"type":{"bibl":"edited-book","media":"Online-Ressource"},"language":["eng"],"title":[{"title_sort":"Arxiv","title":"Arxiv"}],"pubHistory":["1991 -"],"titleAlt":[{"title":"Arxiv.org"},{"title":"Arxiv.org e-print archive"},{"title":"Arxiv e-print archive"},{"title":"De.arxiv.org"}],"part":{"year":"2018","pages":"1-20","extent":"20","text":"(2018), Artikel-ID 1808.04730, Seite 1-20"},"id":{"eki":["509006531"],"zdb":["2225896-6"]}}],"title":[{"title":"Analyzing inverse problems with invertible neural networks","title_sort":"Analyzing inverse problems with invertible neural networks"}],"language":["eng"],"type":{"bibl":"chapter","media":"Online-Ressource"},"note":["Identifizierung der Ressource nach: 6 Feb 2019","Gesehen am 26.07.2022"],"recId":"1810855101","physDesc":[{"extent":"20 S."}],"name":{"displayForm":["Lynton Ardizzone, Jakob Kruse, Sebastian Wirkert, Daniel Rahner, Eric W. Pellegrini, Ralf S. Klessen, Lena Maier-Hein, Carsten Rother, Ullrich Köthe"]},"id":{"eki":["1810855101"],"doi":["10.48550/arXiv.1808.04730"]}} 
SRT |a ARDIZZONELANALYZINGI2018 

Similar Items