Fetching the paper…
Reading the bibliography…
What do artificial neural networks (ANNs) learn? The machine learning (ML) community shares the narrative that ANNs must develop abstract human concepts to perform complex tasks.
Imperceptible adversarial attacks on tabular data
Ballet, V., X. Renard, J. Aigrain, T. Laugel, P. Frossard, and M. Detyniecki. 2019 · 1911
Earlier work this paper cites.
Ontological relativity and other essays
Quine, W.V. 1969 · 1969
Earlier work this paper cites.
Multilayer feedforward networks are universal approximators
Hornik, K., M. Stinchcombe, and H. White. 1989 · 1989
Earlier work this paper cites.
Concepts, kinds, and cognitive development
Keil, F.C. 1992 · 1992
Earlier work this paper cites.
A study of concepts
Peacocke, C. 1992 · 1992
Earlier work this paper cites.
The nature of statistical learning theory
Vapnik, V. 1999 · 1999
Earlier work this paper cites.
The logic of scientific discovery
Popper, K. 2005 · 2005
Earlier work this paper cites.
Concepts as prototypes
Hampton, J.A. 2006 · 2006
Earlier work this paper cites.
On the relationship between class selectivity, dimensionality, and robustness
Leavitt, M.L. and A.S. Morcos. 2020b · 2007
Earlier work this paper cites.
The elements of statistical learning: data mining, inference, and prediction
Hastie, T., R. Tibshirani, J.H. Friedman, and J.H. Friedman. 2009 · 2009
Earlier work this paper cites.
Concepts are a functional kind
Lalumera, E. 2010 · 2010
Earlier work this paper cites.
Towards falsifiable interpretability research
Leavitt, M.L. and A. Morcos. 2020a · 2010
Earlier work this paper cites.
Philosophical investigations
Wittgenstein, L. 2010 · 2010
Earlier work this paper cites.
Statistical learning theory: Models, concepts, and results, Handbook of the History of Logic
Von Luxburg, U. and B. Schölkopf. 2011 · 2011
Earlier work this paper cites.
385 Typicality and Composition a Lity: the Logic of Combining Vague Concepts, The Oxford Handbook of Compositionality
Hampton, J.A. and M.L. Jönsson. 2012, 02 · 2012
Earlier work this paper cites.
Intriguing properties of neural networks
Szegedy, C., W. Zaremba, I. Sutskever, J. Bruna, D. Erhan, I. Goodfellow, and R. Fergus. 2013 · 2013
Earlier work this paper cites.
Explaining and harnessing adversarial examples
Goodfellow, I.J., J. Shlens, and C. Szegedy. 2014 · 2014
Earlier work this paper cites.
Adam: A method for stochastic optimization
Kingma, D.P. and J. Ba. 2014 · 2014
Earlier work this paper cites.
Deep learning
LeCun, Y., Y. Bengio, and G. Hinton. 2015 · 2015
Earlier work this paper cites.
Prototypes as compositional components of concepts
Del Pinal, G. 2016 · 2016
Earlier work this paper cites.
Deep learning
Goodfellow, I., Y. Bengio, and A. Courville. 2016 · 2016
Earlier work this paper cites.
Toward an integration of deep learning and neuroscience
Marblestone, A.H., G. Wayne, and K.P. Kording. 2016 · 2016
Earlier work this paper cites.
”why should i trust you?” explaining the predictions of any classifier
Ribeiro, M.T., S. Singh, and C. Guestrin 2016 · 2016
Earlier work this paper cites.
The Routledge handbook of philosophy of animal minds
Andrews, K. and J. Beck. 2017 · 2017
Earlier work this paper cites.
Network dissection: Quantifying interpretability of deep visual representations
Bau, D., B. Zhou, A. Khosla, A. Oliva, and A. Torralba 2017 · 2017
Earlier work this paper cites.
Brown, T.B., D. Mané, A. Roy, M. Abadi, and J. Gilmer. 2017 · 2017
Earlier work this paper cites.
Machine learning for medical imaging
Erickson, B.J., P. Korfiatis, Z. Akkus, and T.L. Kline. 2017 · 2017
Earlier work this paper cites.
The expressive power of neural networks: A view from the width
Lu, Z., H. Pu, F. Wang, Z. Hu, and L. Wang. 2017 · 2017
Cited alongside, same era.
Feature visualization
Olah, C., A. Mordvintsev, and L. Schubert. 2017 · 2017
Cited alongside, same era.
Learning to generate reviews and discovering sentiment
Radford, A., R. Jozefowicz, and I. Sutskever. 2017 · 2017
Cited alongside, same era.
Attention is all you need
Vaswani, A., N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A.N. Gomez, Ł. Kaiser, and I. Polosukhin. 2017 · 2017
Cited alongside, same era.
Gan dissection: Visualizing and understanding generative adversarial networks
Bau, D., J.Y. Zhu, H. Strobelt, B. Zhou, J.B. Tenenbaum, W.T. Freeman, and A. Torralba 2018 · 2018
Cited alongside, same era.
Empiricism without magic: Transformational abstraction in deep convolutional neural networks
Using deep learning to detect defects in manufacturing: a comprehensive survey and current challenges
Yang, J., S. Li, Z. Wang, H. Dong, J. Wang, and S. Tang. 2020 · 2020
Later among the works it cites.
Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolation
Belkin, M. 2021 · 2021
Later among the works it cites.
Scientific Representation, In The Stanford Encyclopedia of Philosophy
Frigg, R. and J. Nguyen. 2021 · 2021
Later among the works it cites.
Biaswap: Removing dataset bias with bias-tailored swapping augmentation
Kim, E., J. Lee, and J. Choo 2021 · 2021
Later among the works it cites.
Throwing light on black boxes: emergence of visual categories from deep learning
López-Rubio, E. 2021 · 2021
Later among the works it cites.
Deep learning-based weather prediction: a survey
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Buckner, C. 2018 · 2018
Cited alongside, same era.
Imagenet-trained cnns are biased towards texture; increasing shape bias improves accuracy and robustness
Geirhos, R., P. Rubisch, C. Michaelis, M. Bethge, F.A. Wichmann, and W. Brendel 2018 · 2018
Cited alongside, same era.
Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav)
Kim, B., M. Wattenberg, J. Gilmer, C. Cai, J. Wexler, F. Viegas, et al. 2018 · 2018
Cited alongside, same era.
The mythos of model interpretability: In machine learning, the concept of interpretability is both important and slippery
Lipton, Z.C. 2018 · 2018
Cited alongside, same era.
On the importance of single directions for generalization
Morcos, A.S., D.G. Barrett, N.C. Rabinowitz, and M. Botvinick 2018 · 2018
Cited alongside, same era.
The power of deeper networks for expressing natural functions
Rolnick, D. and M. Tegmark 2018 · 2018
Cited alongside, same era.
A survey on deep transfer learning
Tan, C., F. Sun, T. Kong, W. Zhang, C. Yang, and C. Liu 2018 · 2018
Cited alongside, same era.
Ren, X., X. Li, K. Ren, J. Song, Z. Xu, K. Deng, and X. Wang. 2021 · 2021
Later among the works it cites.
Toward causal representation learning
Schölkopf, B., F. Locatello, S. Bauer, N.R. Ke, N. Kalchbrenner, A. Goyal, and Y. Bengio. 2021 · 2021
Later among the works it cites.
Understanding deep learning (still) requires rethinking generalization
Zhang, C., S. Bengio, M. Hardt, B. Recht, and O. Vinyals. 2021 · 2021
Later among the works it cites.
Deep problems with neural network models of human vision
Bowers, J.S., G. Malhotra, M. Dujmović, M.L. Montero, C. Tsvetkov, V. Biscione, G. Puebla, F. Adolfi, J.E. Hummel, R.F. Heaton, et al. 2022 · 2022
Later among the works it cites.
The intriguing relation between counterfactual explanations and adversarial examples
Freiesleben, T. 2022 · 2022
Later among the works it cites.
Freiesleben, T., G. König, C. Molnar, and A. Tejero-Cantero. 2022 · 2022
Later among the works it cites.
Locating and editing factual associations in gpt
Meng, K., D. Bau, A. Andonian, and Y. Belinkov. 2022 · 2022
Later among the works it cites.
Adversarial example detection based on saliency map features
Wang, S. and Y. Gong. 2022 · 2022
Later among the works it cites.
From attribution maps to human-understandable explanations through concept relevance propagation
Achtibat, R., M. Dreyer, I. Eisenbraun, S. Bosse, T. Wiegand, W. Samek, and S. Lapuschkin. 2023 · 2023
Closest in time.
Natural Kinds, In The Stanford Encyclopedia of Philosophy
Bird, A. and E. Tobin. 2023 · 2023
Closest in time.
Functional concept proxies and the actually smart hans problem: What’s special about deep neural networks in science
Boge, F.J. 2023 · 2023
Closest in time.
The representational status of deep learning models
Duede, E. 2023 · 2023
Closest in time.
Beyond generalization: a theory of robustness in machine learning
Freiesleben, T. and T. Grote. 2023 · 2023
Closest in time.
Language models represent space and time
Gurnee, W. and M. Tegmark. 2023 · 2023
Closest in time.
Improvement-focused causal recourse (icr)
König, G., T. Freiesleben, and M. Grosse-Wentrup 2023 · 2023
Closest in time.
Sources of hallucination by large language models on inference tasks
McKenna, N., T. Li, L. Cheng, M.J. Hosseini, M. Johnson, and M. Steedman. 2023 · 2023
Closest in time.
Incorporating a novel dual transfer learning approach for medical images
Mukhlif, A.A., B. Al-Khateeb, and M.A. Mohammed. 2023 · 2023
Closest in time.
Methods for identifying emergent concepts in deep neural networks
Räz, T. 2023 · 2023
Closest in time.
Statistical learning theory and occam’s razor: The argument from empirical risk minimization
Sterkenburg, T.F. 2023 · 2023
Closest in time.
On the philosophy of unsupervised learning
Watson, D.S. 2023 · 2023
Closest in time.
Can chatgpt understand too? a comparative study on chatgpt and fine-tuned bert
Zhong, Q., L. Ding, J. Liu, B. Du, and D. Tao. 2023 · 2023
Closest in time.
Deep convolutional neural networks are not mechanistic explanations of object recognition
Grujičić, B. 2024 · 2024
Closest in time.