This HTML5 document contains 34 embedded RDF statements represented using HTML+Microdata notation.

The embedded RDF content will be recognized by any processor of HTML5 Microdata.

Namespace Prefixes

PrefixIRI
dctermshttp://purl.org/dc/terms/
n2https://kar.kent.ac.uk/id/eprint/
n11https://kar.kent.ac.uk/84806/
wdrshttp://www.w3.org/2007/05/powder-s#
n19http://purl.org/ontology/bibo/status/
dchttp://purl.org/dc/elements/1.1/
n18https://kar.kent.ac.uk/id/subject/
rdfshttp://www.w3.org/2000/01/rdf-schema#
n20https://demo.openlinksw.com/about/id/entity/https/raw.githubusercontent.com/annajordanous/CO644Files/main/
n3http://eprints.org/ontology/
bibohttp://purl.org/ontology/bibo/
n15https://kar.kent.ac.uk/id/publication/
n9https://kar.kent.ac.uk/id/org/
rdfhttp://www.w3.org/1999/02/22-rdf-syntax-ns#
n17doi:10.1016/
n21https://kar.kent.ac.uk/id/eprint/84806#
owlhttp://www.w3.org/2002/07/owl#
n4https://kar.kent.ac.uk/id/document/
n8https://kar.kent.ac.uk/id/
xsdhhttp://www.w3.org/2001/XMLSchema#
n14https://demo.openlinksw.com/about/id/entity/https/www.cs.kent.ac.uk/people/staff/akj22/materials/CO644/
n7https://kar.kent.ac.uk/id/person/

Statements

Subject Item
n2:84806
rdf:type
n3:ArticleEPrint n3:EPrint bibo:AcademicArticle bibo:Article
rdfs:seeAlso
n11:
owl:sameAs
n17:j.neubiorev.2020.09.036
n3:hasAccepted
n4:3223654
n3:hasDocument
n4:3223723 n4:3223724 n4:3223725 n4:3223654 n4:3223657 n4:3223722
dc:hasVersion
n4:3223654
dcterms:title
I tried a bunch of things: The dangers of unexpected overfitting in classification of brain data
wdrs:describedby
n14:export_kar_RDFN3.n3 n20:export_kar_RDFN3.n3
dcterms:date
2020
dcterms:creator
n7:ext-cbf9c2e1cf3aee178e6ce4a1f3cdf589 n7:ext-0677636edb83469617d22c6f10c53ec6 n7:ext-m.n.g.hosseini@kent.ac.uk n7:ext-ebdf05bf031906c52140fb019f5b060f n7:ext-h.bowman@kent.ac.uk n7:ext-aa9a254f2cfb8d1e279b828025184495 n7:ext-0089edc026e5b80ab8f0c3b837963d40
bibo:status
n19:peerReviewed n19:published
dcterms:publisher
n9:ext-f308aad1ef8f70546c3a197f104f2ad5
bibo:abstract
Machine learning has enhanced the abilities of neuroscientists to interpret information collected through EEG, fMRI, and MEG data. With these powerful techniques comes the danger of overfitting of hyperparameters which can render results invalid. We refer to this problem as ‘overhyping’ and show that it is pernicious despite commonly used precautions. Overhyping occurs when analysis decisions are made after observing analysis outcomes and can produce results that are partially or even completely spurious. It is commonly assumed that cross-validation is an effective protection against overfitting or overhyping, but this is not actually true. In this article, we show that spurious results can be obtained on random data by modifying hyperparameters in seemingly innocuous ways, despite the use of cross-validation. We recommend a number of techniques for limiting overhyping, such as lock boxes, blind analyses, pre-registrations, and nested cross-validation. These techniques, are common in other fields that use machine learning, including computer science and physics. Adopting similar safeguards is critical for ensuring the robustness of machine-learning techniques in the neurosciences.
dcterms:isPartOf
n8:repository n15:ext-01497634
dcterms:subject
n18:Q
bibo:authorList
n21:authors
bibo:volume
119