Recognizing handwritten digits using hierarchical products of experts
The DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
Abstract
The product of experts learning procedure can discover a set of stochastic binary features that constitute a nonlinear generative model of handwritten images of digits. The quality of generative models learned in this way can be assessed by learning a separate model for each class of digit and then comparing the unnormalized probabilities of test images under the 10 different class-specific models. To improve discriminative performance, a hierarchy of separate models can be learned, for each digit class. Each model in the hierarchy learns a layer of binary feature detectors that model the probability distribution of vectors of activity of feature detectors in the layer below. The models in the hierarchy are trained sequentially and each model uses a layer of binary feature detectors to learn a generative model of the patterns of feature activities in the preceding layer. After training, each layer of feature detectors produces a separate, unnormalized log probability score. With three layers of feature detectors for each of the 10 digit classes, a test image produces 30 scores which can be used as inputs to a supervised, logistic classification network that is trained on separate data.
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
Wolpert, D. H. (1992) · Neural Networks · doi:10.1016/s0893-6080(05)80023-1 · Cited by 7,951 · cited 1×
“The way in which the individual experts are combined in a Product of Experts generative model has strong similarities to the way in which conditional density models are combined in approaches like stacking [8], bagging [9], or boosting [10].”
BackgroundAdaptive Mixtures of Local Experts
Jacobs, R. A., Jordan, M. I., Nowlan, S. J., & Hinton, G. E. (1991) · Neural Computation · doi:10.1162/neco.1991.3.1.79 · Cited by 5,384
Self-citationTraining Products of Experts by Minimizing Contrastive Divergence
Hinton, G. E. (2002) · Neural Computation · doi:10.1162/089976602760128018 · Cited by 4,879 · cited 4×
“HINTON [1] describes a learning algorithm for probabilistic generative models that are composed of a number of experts.”
BackgroundInfluentialSelf-citationLearning and relearning in Boltzmann machines
Hinton, G. E., & Sejnowski, T. J. (2001) · Graphical Models · doi:10.7551/mitpress/3349.003.0005 · Cited by 1,037
Self-citation
Cited by
A fast learning algorithm for deep belief nets
Hinton, G. E., Osindero, S., & Teh, Y.-W. (2006) · Neural Computation · doi:10.1162/neco.2006.18.7.1527 · Cited by 16,336
Self-citationTraining Products of Experts by Minimizing Contrastive Divergence
Hinton, G. E. (2002) · Neural Computation · doi:10.1162/089976602760128018 · Cited by 4,879
Self-citationHandwritten digit recognition: benchmarking of state-of-the-art techniques
Liu, C.-L., Nakashima, K., Sako, H., & Fujisawa, H. (2003) · Pattern Recognition · doi:10.1016/s0031-3203(03)00085-2 · Cited by 543
Zilly, J., Buhmann, J. M., & Mahapatra, D. (2017) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2016.07.012 · Cited by 372
Hinton, G. E. (1999) · 9th International Conference on Artificial Neural Networks: ICANN '99 · doi:10.1049/cp:19991075 · Cited by 341
Self-citationDeformation Models for Image Recognition
Keysers, D., Deselaers, T., Gollan, C., & Ney, H. (2007) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2007.1153 · Cited by 255
Hierarchical Neural Networks for Image Interpretation
Behnke, S. (2003) · Lecture Notes in Computer Science · doi:10.1007/b11963 · Cited by 225
Cunningham, R. J., & Loram, I. D. (2020) · Journal of The Royal Society Interface · doi:10.1098/rsif.2019.0715 · Cited by 36
“such as restricted Boltzmann machines [45], [56], deep belief”
BackgroundMethod
Metadata
- Authors
- Mayraz, G., & Hinton, G. E.
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2002
- Volume
- 24
- Issue
- 2
- Pages
- 189-197
- ISSN
- 0162-8828 (ISSN-L)
- OpenAlex
- W2097119693
- Cited by
- 78
- References
- 4
- FWCI
- 6.37
- Type
- journal article
- Language
- en
- Open access
- closed
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.