Fetching the paper…
Reading the bibliography…
This paper aims to clarify the representational status of Deep Learning Models (DLMs).
Models of data
Patrick Suppes · 1966
Earlier work this paper cites.
The scientific image
Bas C Van Fraassen et al · 1980
Earlier work this paper cites.
Knowledge and the Flow of Information
Fred Dretske · 1981
Earlier work this paper cites.
How the laws of physics lie, 1984
Nancy Cartwright and Ernan McMullin · 1984
Earlier work this paper cites.
Distributed representations
Geoffrey E Hinton · 1984
Earlier work this paper cites.
A general framework for parallel distributed processing
David E Rumelhart, Geoffrey E Hinton, James L McClelland, et al · 1986
Earlier work this paper cites.
Learning representations by back-propagating errors
David E Rumelhart, Geoffrey E Hinton, and Ronald J Williams · 1986
Earlier work this paper cites.
False models as means to truer theories
William C Wimsatt · 1987
Earlier work this paper cites.
Connectionism and cognitive architecture: A critical analysis
Jerry A Fodor and Zenon W Pylyshyn · 1988
Earlier work this paper cites.
Biosemantics
Ruth Garrett Millikan · 1989
Earlier work this paper cites.
Explaining behavior: Reasons in a world of causes
Fred Dretske · 1991
Earlier work this paper cites.
Misrepresenting & malfunctioning
Karen Neander · 1995
Earlier work this paper cites.
Last Writings on the Philosophy of Psychology, volume 1
Ludwig Wittgenstein · 1996
Earlier work this paper cites.
Modeling evolution in theory and practice
Anya Plutynski · 2001
Earlier work this paper cites.
Science and partial truth: A unitary approach to models and scientific reasoning
Newton CA Da Costa and Steven French · 2003
Earlier work this paper cites.
A model-theoretic account of representation (or, i don’t know much about art… but i know it involves isomorphism)
Steven French · 2003
Earlier work this paper cites.
Scientific representation: Against similarity and isomorphism
Mauricio Suárez · 2003
Earlier work this paper cites.
How models are used to represent reality
Ronald N Giere · 2004
Earlier work this paper cites.
Extending ourselves: Computational science, empiricism, and scientific method
Paul Humphreys · 2004
Earlier work this paper cites.
An inferential conception of scientific representation
Mauricio Suárez · 2004
Earlier work this paper cites.
Scientific representation, interpretation, and surrogative reasoning
Gabriele Contessa · 2007
Earlier work this paper cites.
Misrepresentations
Inman Harvey · 2008
Earlier work this paper cites.
Models as epistemic tools in engineering sciences
Mieke Boon and Tarja Knuuttila · 2009
Earlier work this paper cites.
Visualizing higher-layer features of a deep network
Dumitru Erhan, Y. Bengio, Aaron Courville, and Pascal Vincent · 2009
Earlier work this paper cites.
On the explanatory role of mathematics in empirical science
Robert W Batterman · 2010
Earlier work this paper cites.
Fiction and scientific representation
Roman Frigg · 2010
Earlier work this paper cites.
Explaining science: A cognitive approach
Ronald N Giere · 2010
Earlier work this paper cites.
Scientific representation: Paradoxes of perspective, 2010
Bas C Van Fraassen · 2010
Earlier work this paper cites.
Machine learning: the art and science of algorithms that make sense of data
Peter Flach · 2012
Earlier work this paper cites.
Optimality explanations: A plea for an alternative approach
Collin Rice · 2012
Earlier work this paper cites.
Simulation and similarity: Using models to understand the world
Michael Weisberg · 2012
Earlier work this paper cites.
Representation learning: A review and new perspectives
Yoshua Bengio, Aaron Courville, and Pascal Vincent · 2013
Earlier work this paper cites.
Interpreting individual classifications of hierarchical networks
Will Landecker, Michael D Thomure, Luís MA Bettencourt, Melanie Mitchell, Garrett T Kenyon, and Steven P Brumby · 2013
Earlier work this paper cites.
Intriguing properties of neural networks
Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, and Rob Fergus · 2013
Cited alongside, same era.
Minimal model explanations
Robert W Batterman and Collin C Rice · 2014
Cited alongside, same era.
Deep neural networks rival the representation of primate it cortex for core visual object recognition
Charles F Cadieu, Ha Hong, Daniel LK Yamins, Nicolas Pinto, Diego Ardila, Ethan A Solomon, Najib J Majaj, and James J DiCarlo · 2014
Cited alongside, same era.
Rich feature hierarchies for accurate object detection and semantic segmentation
Ross Girshick, Jeff Donahue, Trevor Darrell, and Jitendra Malik · 2014
Cited alongside, same era.
On “minimal model explanations”: A reply to batterman and rice
Marc Lange · 2015
Cited alongside, same era.
Deep learning
Massive computational acceleration by using neural networks to emulate mechanism-based biological models
Shangying Wang, Fan Kai, Nan Luo, Yangxiaolu Cao, Feilun Wu, Carolyn Zhang, Katherine A Heller, and Lingchong You · 2019
Later among the works it cites.
The generalizability crisis
Tal Yarkoni · 2019
Later among the works it cites.
Humans can decipher adversarial images
Zhenglong Zhou and Chaz Firestone · 2019
Later among the works it cites.
Overinterpretation reveals image classification model pathologies
Brandon Carter et al · 2020
Later among the works it cites.
Transparency in complex computational systems
Kathleen A Creel · 2020
Later among the works it cites.
Underspecification presents challenges for credibility in modern machine learning
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Yann LeCun, Yoshua Bengio, and Geoffrey Hinton · 2015
Cited alongside, same era.
Modeling without models
Arnon Levy · 2015
Cited alongside, same era.
Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
Anh Nguyen, Jason Yosinski, and Jeff Clune · 2015
Cited alongside, same era.
The fiction view of models reloaded
Roman Frigg and James Nguyen · 2016
Cited alongside, same era.
Deep learning
Ian Goodfellow, Yoshua Bengio, and Aaron Courville · 2016
Cited alongside, same era.
A taxonomy of emergent trusting in the human–machine relationship
Robert R Hoffman · 2017
Cited alongside, same era.
Sanity checks for saliency maps
Julius Adebayo, Justin Gilmer, Michael Muelly, Ian Goodfellow, Moritz Hardt, and Been Kim · 2018
Cited alongside, same era.
Alexander D’Amour, Katherine Heller, Dan Moldovan, Ben Adlam, Babak Alipanahi, Alex Beutel, Christina Chen, Jonathan Deaton, Jacob Eisenstein, Matthew D Hoffman, et al · 2020
Later among the works it cites.
Modelling nature: An opinionated introduction to scientific representation
Roman Frigg, James Nguyen, et al · 2020
Later among the works it cites.
Shortcut learning in deep neural networks
Robert Geirhos et al · 2020
Later among the works it cites.
Towards falsifiable interpretability research
Matthew L Leavitt and Ari Morcos · 2020
Later among the works it cites.
Model evaluation: An adequacy-for-purpose view
Wendy S Parker · 2020
Later among the works it cites.
A survey of deep learning for scientific discovery
Maithra Raghu and Eric Schmidt · 2020
Later among the works it cites.
Improved protein structure prediction using potentials from deep learning
Andrew W Senior, Richard Evans, et al · 2020
Later among the works it cites.
From implausible artificial neurons to idealized cognitive models: Rebooting philosophy of artificial intelligence
Catherine Stinson · 2020
Later among the works it cites.
A philosophical understanding of representation for neuroscience
Ben Baker et al · 2021
Later among the works it cites.
Two dimensions of opacity and the deep learning predicament
Florian J Boge · 2021
Later among the works it cites.
Representationalism is a dead end
Guilherme Sanches de Oliveira · 2021
Later among the works it cites.
Governing ai safety through independent audits
Gregory Falco, Ben Shneiderman, et al · 2021
Later among the works it cites.
Might a single neuron solve interesting machine learning problems through successive computations on its dendritic tree?
Ilenna Simone Jones and Konrad Paul Kording · 2021
Later among the works it cites.
Why ai is harder than we think
Melanie Mitchell · 2021
Later among the works it cites.
Clinical decisions using ai must consider patient values
Jonathan Birch, Kathleen A Creel, et al · 2022
Later among the works it cites.
Three aspects of representation in neuroscience
Ben Baker, Benjamin Lansdell, and Konrad P Kording · 2022
Later among the works it cites.
Putting representations to use
Rosa Cao · 2022
Later among the works it cites.
Deep learning opacity in scientific discovery
Eamon Duede · 2022
Later among the works it cites.
Instruments, agents, and artificial intelligence: novel epistemic categories of reliability
Eamon Duede · 2022
Later among the works it cites.
In-context learning and induction heads
Catherine Olsson, Nelson Elhage, Neel Nanda, Nicholas Joseph, Nova DasSarma, Tom Henighan, Ben Mann, Amanda Askell, Yuntao Bai, Anna Chen, et al · 2022
Later among the works it cites.
Understanding deep learning with statistical relevance
Tim Räz · 2022
Later among the works it cites.
The importance of understanding deep learning
Tim Räz and Claus Beisbart · 2022
Later among the works it cites.
Machine behaviour
Iyad Rahwan, Manuel Cebrian, Nick Obradovich, Josh Bongard, Jean-François Bonnefon, Cynthia Breazeal, Jacob W Crandall, Nicholas A Christakis, Iain D Couzin, Matthew O Jackson, et al · 2022
Later among the works it cites.
Talking about large language models
Murray Shanahan · 2022
Later among the works it cites.
Understanding from machine learning models
Emily Sullivan · 2022
Later among the works it cites.
Explaining machine learning decisions
John Zerilli · 2022
Later among the works it cites.
Does the no miracles argument apply to ai?
Darrell P Rowbottom, William Peden, and André Curtis-Trudel · 2024
Closest in time.