Better Digit Recognition with a Committee of Simple Neural Nets
The DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
Abstract
We present a new method to train the members of a committee of one-hidden-layer neural nets. Instead of training various nets on subsets of the training data we preprocess the training data for each individual model such that the corresponding errors are decor related. On the MNIST digit recognition benchmark set we obtain a recognition error rate of 0.39%, using a committee of 25 one-hidden-layer neural nets, which is on par with state-of-the-art recognition rates of more complicated systems.
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
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
Training Products of Experts by Minimizing Contrastive Divergence
Hinton, G. E. (2002) · Neural Computation · doi:10.1162/089976602760128018 · Cited by 4,879
Sparse coding with an overcomplete basis set: A strategy employed by V1?
Olshausen, B. A., & Field, D. J. (1997) · Vision Research · doi:10.1016/s0042-6989(97)00169-7 · Cited by 3,642
Efficient Learning of Sparse Representations with an Energy-Based Model
Ranzato, M., Poultney, C., Chopra, S., & LeCun, Y. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0147 · Cited by 1,106
Cited by
(2011) · doi:10.5591/978-1-57735-516-8/ijcai11-210 · Cited by 1,229
Self-citationMulti-column deep neural network for traffic sign classification
Cireşan, D., Meier, U., Masci, J., & Schmidhuber, J. (2012) · Neural Networks · doi:10.1016/j.neunet.2012.02.023 · Cited by 1,057
“For handwritten digits it was shown (Meier et al., 2011), that simply averaging the outputs of many DNN generalizes better on the test set than a combination of all the DNN with weights over a set ( Hashem & Schmeiser, 1995 ; Ueda, 2000).”
BackgroundMethodSelf-citationVehicle Detection in Satellite Images by Hybrid Deep Convolutional Neural Networks
Chen, X., Xiang, S., Liu, C.-L., & Pan, C.-H. (2014) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2014.2309695 · Cited by 622
Steel defect classification with Max-Pooling Convolutional Neural Networks
Masci, J., Meier, U., Ciresan, D., Schmidhuber, J., & Fricout, G. (2012) · The 2012 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2012.6252468 · Cited by 345
“To avoid this problem predictions of various classifiers trained on differently normalized data can be combined [27].”
BackgroundSelf-citationA Survey of Handwritten Character Recognition with MNIST and EMNIST
Baldominos, A., Saez, Y., & Isasi, P. (2019) · Applied Sciences · doi:10.3390/app9153169 · Cited by 279
“Test Error Rate NN 6-layer 5,700 hidden units [12] 0.35% MSRV C-SVDDNet [46] 0.35% Committee of 25 NN 2-layer 800 hidden units [11] 0.39% RNN [48] 0.45% K-NN (P2DHMDM) [6] 0.52% COSFIRE [49] 0.52% K-NN (IDM) [6] 0.54% Task-driven dictionary learning [51] 0.54% Virtual SVM, deg-9 poly, 2-pixel jit…”
ResultInfluential
Metadata
- Authors
- Meier, U., Ciresan, D. C., Gambardella, L. M., & Schmidhuber, J.
- Venue
- 2011 International Conference on Document Analysis and Recognition
- Publisher
- IEEE
- Published
- 2011-09
- Pages
- 1250-1254
- ISSN
- 1520-5363 (ISSN-L)
- OpenAlex
- W2117356902
- Cited by
- 69
- References
- 4
- FWCI
- 4.77
- Type
- conference paper
- 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.