Where Do Features Come From?
The DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index.
Abstract
It is possible to learn multiple layers of non‐linear features by backpropagating error derivatives through a feedforward neural network. This is a very effective learning procedure when there is a huge amount of labeled training data, but for many learning tasks very few labeled examples are available. In an effort to overcome the need for labeled data, several different generative models were developed that learned interesting features by modeling the higher order statistical structure of a set of input vectors. One of these generative models, the restricted Boltzmann machine (RBM), has no connections between its hidden units and this makes perceptual inference and learning much simpler. More significantly, after a layer of hidden features has been learned, the activities of these features can be used as training data for another RBM. By applying this idea recursively, it is possible to learn a deep hierarchy of progressively more complicated features without requiring any labeled data. This deep hierarchy can then be treated as a feedforward neural network which can be discriminatively fine‐tuned using backpropagation. Using a stack of RBMs to initialize the weights of a feedforward neural network allows backpropagation to work effectively in much deeper networks and it leads to much better generalization. A stack of RBMs can also be used to initialize a deep Boltzmann machine that has many hidden layers. Combining this initialization method with a new method for fine‐tuning the weights finally leads to the first efficient way of training Boltzmann machines with many hidden layers and millions of weights.
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
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
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
Learning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892
Self-citationGaussian Processes for Machine Learning
Rasmussen, C. E., & Williams, C. K. I. (2005) · doi:10.7551/mitpress/3206.001.0001 · Cited by 11,705
Learning long-term dependencies with gradient descent is difficult
Bengio, Y., Simard, P., & Frasconi, P. (1994) · IEEE Transactions on Neural Networks · doi:10.1109/72.279181 · Cited by 8,542 · cited 1×
“For dynamic data, the most natural way to reconstruct the input data was to predict the next frame of data [9], but attempts to apply backpropagation-through-time to learning sequential data failed because the gradients grew or shrank multiplicatively at each time step [3].”
MethodTraining Products of Experts by Minimizing Contrastive Divergence
Hinton, G. E. (2002) · Neural Computation · doi:10.1162/089976602760128018 · Cited by 4,879 · cited 1×
“Initially, they were not particularly interested in learning because they intended to use domain experts to specify the way in which the probability distribution of each discrete variable depended on the values of its parents.”
BackgroundSelf-citation(2010) · Journal of Machine Learning Research · doi:10.5555/1756006.1953039 · Cited by 4,051
An Introduction to Variational Methods for Graphical Models
Jordan, M. I., Ghahramani, Z., Jaakkola, T. S., & Saul, L. K. (1999) · Machine Learning · doi:10.1023/a:1007665907178 · Cited by 3,791
Phoneme recognition using time-delay neural networks
Waibel, A., Hanazawa, T., Hinton, G., Shikano, K., & Lang, K. J. (1989) · IEEE Transactions on Acoustics, Speech, and Signal Processing · doi:10.1109/29.21701 · Cited by 2,643
Self-citationLee, H., Grosse, R., Ranganath, R., & Ng, A. Y. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553453 · Cited by 2,412
A View of the Em Algorithm that Justifies Incremental, Sparse, and other Variants
Neal, R. M., & Hinton, G. E. (1998) · Learning in Graphical Models · doi:10.1007/978-94-011-5014-9_12 · Cited by 2,187
Self-citationA free energy principle for the brain
Friston, K., Kilner, J., & Harrison, L. (2006) · Journal of Physiology-Paris · doi:10.1016/j.jphysparis.2006.10.001 · Cited by 1,369
Hinton, G. E., Krizhevsky, A., & Wang, S. D. (2011) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-21735-7_6 · Cited by 1,360
Self-citationThe "Wake-Sleep" Algorithm for Unsupervised Neural Networks
Hinton, G. E., Dayan, P., Frey, B. J., & Neal, R. M. (1995) · Science · doi:10.1126/science.7761831 · Cited by 1,070
Self-citationTheory-based Bayesian models of inductive learning and reasoning
Tenenbaum, J. B., Griffiths, T. L., & Kemp, C. (2006) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2006.05.009 · Cited by 880 · cited 1×
“We can investigate people's learning abilities without worrying about the hardware [50], we can investigate how real synapses change [31], or we can explore the space of synaptic learning rules that work well in large networks of neuron-like processors.”
BackgroundCrick, F., & Mitchison, G. (1983) · Nature · doi:10.1038/304111a0 · Cited by 865
Buesing, L., Bill, J., Nessler, B., & Maass, W. (2011) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1002211 · Cited by 384
Using fast weights to improve persistent contrastive divergence
Tieleman, T., & Hinton, G. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553506 · Cited by 274 · cited 1×
“So the energy landscape is modified to raise the energy of whatever s tate a persisitent chain is currently in [51, 52].”
BackgroundSelf-citation
Cited by
Deep Learning in Drug Discovery
Gawehn, E., Hiss, J. A., & Schneider, G. (2016) · Molecular Informatics · doi:10.1002/minf.201501008 · Cited by 723
An Efficient Learning Procedure for Deep Boltzmann Machines
Salakhutdinov, R., & Hinton, G. (2012) · Neural Computation · doi:10.1162/neco_a_00311 · Cited by 484
Self-citationHuman emotion recognition using deep belief network architecture
Hassan, M. M., Alam, M. G. R., Uddin, M. Z., Huda, S., Almogren, A., & Fortino, G. (2019) · Information Fusion · doi:10.1016/j.inffus.2018.10.009 · Cited by 307
Deep learning based classification of breast tumors with shear-wave elastography
Zhang, Q., Xiao, Y., Dai, W., Suo, J., Wang, C., Shi, J., & Zheng, H. (2016) · Ultrasonics · doi:10.1016/j.ultras.2016.08.004 · Cited by 240
Interactive Activation and Mutual Constraint Satisfaction in Perception and Cognition
McClelland, J. L., Mirman, D., Bolger, D. J., & Khaitan, P. (2014) · Cognitive Science · doi:10.1111/cogs.12146 · Cited by 122
Metadata
- Authors
- Hinton, G.
- Venue
- Cognitive Science
- Publisher
- Wiley
- Published
- 2013-06-25
- Volume
- 38
- Issue
- 6
- Pages
- 1078-1101
- ISSN
- 0364-0213 (ISSN-L)
- 1551-6709
- OpenAlex
- W2084336274
- Cited by
- 106
- References
- 18
- FWCI
- 6.99
- 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.