Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
  Mixed Integer Neural Inverse Design

Ansari, N., Seidel, H.-P., & Babaei, V. (2021). Mixed Integer Neural Inverse Design. Retrieved from https://arxiv.org/abs/2109.12888.

Item is

Basisdaten

einblenden: ausblenden:
Genre: Forschungspapier

Dateien

einblenden: Dateien
ausblenden: Dateien
:
arXiv:2109.12888.pdf (Preprint), 26MB
Name:
arXiv:2109.12888.pdf
Beschreibung:
File downloaded from arXiv at 2021-11-04 14:15
OA-Status:
Sichtbarkeit:
Öffentlich
MIME-Typ / Prüfsumme:
application/pdf / [MD5]
Technische Metadaten:
Copyright Datum:
-
Copyright Info:
-

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
Ansari, Navid1, Autor           
Seidel, Hans-Peter1, Autor           
Babaei, Vahid1, Autor           
Affiliations:
1Computer Graphics, MPI for Informatics, Max Planck Society, ou_40047              

Inhalt

einblenden:
ausblenden:
Schlagwörter: Computer Science, Graphics, cs.GR,Computer Science, Learning, cs.LG
 Zusammenfassung: In computational design and fabrication, neural networks are becoming
important surrogates for bulky forward simulations. A long-standing,
intertwined question is that of inverse design: how to compute a design that
satisfies a desired target performance? Here, we show that the piecewise linear
property, very common in everyday neural networks, allows for an inverse design
formulation based on mixed-integer linear programming. Our mixed-integer
inverse design uncovers globally optimal or near optimal solutions in a
principled manner. Furthermore, our method significantly facilitates emerging,
but challenging, combinatorial inverse design tasks, such as material
selection. For problems where finding the optimal solution is not desirable or
tractable, we develop an efficient yet near-optimal hybrid optimization.
Eventually, our method is able to find solutions provably robust to possible
fabrication perturbations among multiple designs with similar performances.

Details

einblenden:
ausblenden:
Sprache(n): eng - English
 Datum: 2021-09-272021
 Publikationsstatus: Online veröffentlicht
 Seiten: 11 p.
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: arXiv: 2109.12888
URI: https://arxiv.org/abs/2109.12888
BibTex Citekey: Ansari_2109.12888
 Art des Abschluß: -

Veranstaltung

einblenden:

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle

einblenden: