123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081 |
- authors:
- -
- firstname: "Lukas"
- lastname: "Muttenthaler"
- affiliation: "Google DeepMind, Machine Learning Group, Technische Universität Berlin, BIFOLD, Berlin Institute for the Foundations of
- Learning and Data, Berlin, Germany"
- id: "ORCID:0000-0002-0804-4687"
- -
- firstname: "Klaus"
- lastname: "Greff"
- affiliation: "Google DeepMind"
- id: "ORCID:0000-0001-6982-0937"
- -
- firstname: "Frieda"
- lastname: "Born"
- affiliation: "Technische Universität Berlin, BIFOLD, Berlin Institute for the Foundations of
- Learning and Data, Berlin, Germany, Adaptive Memory and Decision Making (AMD), Max Planck Institute for Human Development,Berlin, Germany"
- id: "ORCID:0009-0002-1214-4864"
- -
- firstname: "Bernhard"
- lastname: "Spitzer"
- affiliation: "Adaptive Memory and Decision Making (AMD), Max Planck Institute for Human Development, Berlin, Germany"
- id: "ORCID:0000-0001-9752-932X"
- -
- firstname: "Simon"
- lastname: "Kornblith"
- affiliation: "Anthropic"
- id: "ORCID:0000-0002-9088-2443"
- -
- firstname: "Michael C."
- lastname: "Mozer"
- affiliation: "Google DeepMind"
- id: "ORCID:0000-0002-9654-0575"
- -
- firstname: "Klaus-Robert"
- lastname: "Müller"
- affiliation: "Google DeepMind, Machine Learning Group, Technische Universität Berlin, BIFOLD, Berlin Institute for the Foundations of
- Learning and Data, Berlin, Germany,Department of Artificial Intelligence, Korea University, Seoul, Max Planck Institute for Informatics, Saarbrücken, Germany"
- id: "ORCID:0000-0002-3861-7685"
- -
- firstname: "Thomas"
- lastname: "Unterthiner"
- affiliation: "Google DeepMind"
- id: "ORCID:0000-0001-5361-3087"
- -
- firstname: "Andrew K."
- lastname: "Lampinen"
- affiliation: "Google DeepMind"
- id: "ORCID:0000-0002-6988-8437"
- title: "The Levels Dataset"
- description:
- To validate that AligNet can indeed help to increase the alignment between models and humans,
- we used crowd-sourcing to collect a novel evaluation dataset of human semantic judgments across
- multiple levels of abstraction that we call Levels.
- keywords:
- - AI alignment
- - human cognition
- - representation learning
- - computer vision
- references:
- -
- id: doi:10.48550/arXiv.2409.06509
- reftype: "IsSupplementTo"
- citation: "Muttenthaler, L., Greff, K., Born, F., Spitzer, B., Kornblith, S., Mozer, M.C., Müller, K.R., Unterthiner, T., Lampinen, A.K. : Aligning Machine and Human Visual Representations across Abstraction Levels"
- -
- id: doi:10.5281/zenodo.13749102
- reftype: "IsReferencedBy"
- citation: "Born Frieda. (2024). Levels Collection Experiment Code (v1.0.0)"
- license:
- name: "Open Data Commons Public Domain Dedication and License (PDDL) v1.0"
- url: "https://opendatacommons.org/licenses/pddl/1-0/"
- resourcetype: Dataset
- templateversion: 1.1
|