SwePub
Sök i LIBRIS databas

  Extended search

id:"swepub:oai:DiVA.org:kth-279200"
 

Search: id:"swepub:oai:DiVA.org:kth-279200" > Fibers of Failure :

  • 1 of 1
  • Previous record
  • Next record
  •    To hitlist
  • Carlsson, Leo S.KTH,Materialvetenskap (author)

Fibers of Failure : Classifying Errors in Predictive Processes

  • Article/chapterEnglish2020

Publisher, publication year, extent ...

  • 2020-06-23
  • MDPI,2020
  • printrdacarrier

Numbers

  • LIBRIS-ID:oai:DiVA.org:kth-279200
  • https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-279200URI
  • https://doi.org/10.3390/a13060150DOI

Supplementary language notes

  • Language:English
  • Summary in:English

Part of subdatabase

Classification

  • Subject category:ref swepub-contenttype
  • Subject category:art swepub-publicationtype

Notes

  • QC 20200818
  • Predictive models are used in many different fields of science and engineering and are always prone to make faulty predictions. These faulty predictions can be more or less malignant depending on the model application. We describe fibers of failure (FIFA), a method to classify failure modes of predictive processes. Our method uses MAPPER, an algorithm from topological data analysis (TDA), to build a graphical model of input data stratified by prediction errors. We demonstrate two ways to use the failure mode groupings: either to produce a correction layer that adjusts predictions by similarity to the failure modes; or to inspect members of the failure modes to illustrate and investigate what characterizes each failure mode. We demonstrate FIFA on two scenarios: a convolutional neural network (CNN) predicting MNIST images with added noise, and an artificial neural network (ANN) predicting the electrical energy consumption of an electric arc furnace (EAF). The correction layer on the CNN model improved its prediction accuracy significantly while the inspection of failure modes for the EAF model provided guiding insights into the domain-specific reasons behind several high-error regions.

Subject headings and genre

Added entries (persons, corporate bodies, meetings, titles ...)

  • Vejdemo-Johansson, MikaelCUNY Coll Staten Isl, Dept Math, 2800 Victory Blvd, Staten Isl, NY 10314 USA.;CUNY, Comp Sci, Grad Ctr, 365 5th Ave, New York, NY 10016 USA. (author)
  • Carlsson, GunnarStanford Univ, Dept Math, 450 Serra Mall, Stanford, CA 94305 USA.;Unbox AI, Stanford, CA 94305 USA. (author)
  • Jönsson, Pär G.KTH,Materialvetenskap(Swepub:kth)u118w09b (author)
  • KTHMaterialvetenskap (creator_code:org_t)

Related titles

  • In:Algorithms: MDPI13:61999-4893

Internet link

Find in a library

  • Algorithms (Search for host publication in LIBRIS)

To the university's database

  • 1 of 1
  • Previous record
  • Next record
  •    To hitlist

Search outside SwePub

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

 
pil uppåt Close

Copy and save the link in order to return to this view