The DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.
When and Why Are Deep Networks Better Than Shallow Ones?
Open accessAbstract
While the universal approximation property holds both for hierarchical and shallow networks, deep networks can approximate the class of compositional functions as well as shallow networks but with exponentially lower number of training parameters and sample complexity. Compositional functions are obtained as a hierarchy of local constituent functions, where "local functions'' are functions with low dimensionality. This theorem proves an old conjecture by Bengio on the role of depth in networks, characterizing precisely the conditions under which it holds. It also suggests possible answers to the the puzzle of why high-dimensional deep networks trained on large training sets often do not seem to show overfit.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Fukushima, K. (1980) · Biological Cybernetics · doi:10.1007/bf00344251 · Cited by 5,759 · cited 1×
“The Neocognitron (Fukushima 1980) was a convolutional neural network that was trained to recognize characters.”
BackgroundHierarchical models of object recognition in cortex
Riesenhuber, M., & Poggio, T. (1999) · Nature Neuroscience · doi:10.1038/14819 · Cited by 3,309 · cited 1×
“The property of compositionality was a main motivation for hierarchical models of visual cortex such as HMAX which can be regarded as a pyramid of AND and OR layers (Riesenhuber and Poggio 1999), that is a sequence of conjunctions and disjunctions.”
BackgroundSelf-citationOn the Number of Linear Regions of Deep Neural Networks
Montúfar, G., Pascanu, R., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1402.1869 · Cited by 840
Why and when can deep-but not shallow-networks avoid the curse of dimensionality: A review
Poggio, T., Mhaskar, H., Rosasco, L., Miranda, B., & Liao, Q. (2017) · International Journal of Automation and Computing · doi:10.1007/s11633-017-1054-2 · Cited by 559
Self-citationWhy Does Deep and Cheap Learning Work So Well?
Lin, H. W., Tegmark, M., & Rolnick, D. (2017) · Journal of Statistical Physics · doi:10.1007/s10955-017-1836-5 · Cited by 393
Unsupervised learning of invariant representations
Anselmi, F., Leibo, J. Z., Rosasco, L., Mutch, J., Tacchetti, A., & Poggio, T. (2016) · Theoretical Computer Science · doi:10.1016/j.tcs.2015.06.048 · Cited by 88 · cited 1×
“In addition, both shallow and deep representations may or may not reflect invariance to group transformations of the inputs of the function ( (Soatto 2011; Anselmi et al. 2015)).”
BackgroundSelf-citationSoatto, S. (2011) · arXiv · doi:10.48550/arxiv.1110.2053 · Cited by 40 · cited 1×
“In addition, both shallow and deep representations may or may not reflect invariance to group transformations of the inputs of the function ( (Soatto 2011; Anselmi et al. 2015)).”
Background
Cited by
Deep Forest: Towards An Alternative to Deep Neural Networks
Zhou, Z.-H., & Feng, J. (2017) · Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2017/497 · Cited by 935
Deep learning in medical imaging and radiation therapy
Sahiner, B., Pezeshk, A., Hadjiiski, L. M., Wang, X., Drukker, K., Cha, K. H., Summers, R. M., & Giger, M. L. (2019) · Medical Physics · doi:10.1002/mp.13264 · Cited by 740
Machine learning advances for time series forecasting
Masini, R. P., Medeiros, M. C., & Mendes, E. F. (2023) · Journal of Economic Surveys · doi:10.1111/joes.12429 · Cited by 515
Why ResNet Works? Residuals Generalize
He, F., Liu, T., & Tao, D. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.2966319 · Cited by 406
Model complexity of deep learning: a survey
Hu, X., Chu, L., Pei, J., Liu, W., & Bian, J. (2021) · Knowledge and Information Systems · doi:10.1007/s10115-021-01605-0 · Cited by 402
Metadata
- Authors
- Mhaskar, H., Liao, Q., & Poggio, T.
- Venue
- Proceedings of the AAAI Conference on Artificial Intelligence
- Published
- 2017-02-13
- Volume
- 31
- Issue
- 1
- ISSN
- 2159-5399 (ISSN-L)
- 2374-3468
- OpenAlex
- W2604268533
- Cited by
- 168
- References
- 8
- FWCI
- 8.64
- Type
- conference paper
- Language
- en
- Open access
- diamond
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.