Finding Influential Examples in Deep Learning Models

Visa enkel post
dc.contributor.authorBrinkman, Adam
dc.contributor.authorLarsson Hörkén, Johan
dc.contributor.departmentChalmers tekniska högskola / Institutionen för matematiska vetenskapersv
dc.contributor.examinerJonasson, Johan
dc.contributor.supervisorJörnsten, Rebecka
dc.date.accessioned2021-01-25T12:28:30Z
dc.date.available2021-01-25T12:28:30Z
dc.date.issued2021sv
dc.date.submitted2020
dc.description.abstractMachine learning models are powerful, but not without errors and the complexity of large models makes it hard for a human to intuitively understand the cause of the error. This thesis approaches the task of explaining predictions made by deep learning models by studying the importance of specific examples in the training data, referred to as influence. In practice, the embedding representation of the training data, defined as the output from an arbitrary layer in the model, is compared to the influence on a prediction. Two models are investigated; a Logistic Regression model and a Convolutional Neural Network. The aim of this thesis is thus to identify influential examples in deep learning models in a computationally efficient way, by studying the relation between the representation of the data in a network and its influence. The main results include comparisons between various metrics of distance in the embedding representation of the images to their influence. Similar examples are shown to be clustered close together, training examples close to a test example exhibited high influence for a correctly classified test example. Training examples far away from its class centroid in the embedding space also show high influence.sv
dc.identifier.coursecodeMVEX03sv
dc.identifier.urihttps://hdl.handle.net/20.500.12380/302167
dc.language.isoengsv
dc.setspec.uppsokPhysicsChemistryMaths
dc.subjectinfluence, convolutional, network, embedding, features, similaritysv
dc.titleFinding Influential Examples in Deep Learning Modelssv
dc.type.degreeExamensarbete för masterexamensv
dc.type.uppsokH
local.programmeEngineering mathematics and computational science (MPENM), MSc
Ladda ner
Original bundle
Visar 1 - 1 av 1
Bild (thumbnail)
Namn:
Finding Influential Examples in Deep Learning Models.pdf
Storlek:
2.65 MB
Format:
Adobe Portable Document Format
Beskrivning:
Ladda ner
License bundle
Visar 1 - 1 av 1
Bild (thumbnail)
Namn:
license.txt
Storlek:
1.14 KB
Format:
Item-specific license agreed upon to submission
Beskrivning:
Ladda ner
Samling
Examensarbeten för masterexamen