Computation with Infinite Neural Networks
The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Abstract
For neural networks with a wide class of weight priors, it can be shown that in the limit of an infinite number of hidden units, the prior over functions tends to a gaussian process. In this article, analytic forms are derived for the covariance function of the gaussian processes corresponding to networks with sigmoidal and gaussian hidden units. This allows predictions to be made efficiently using networks with an infinite number of hidden units and shows, somewhat paradoxically, that it may be easier to carry out Bayesian prediction with infinite networks rather than finite ones.
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
A practical Bayesian framework for backpropagation networks
MacKay, D. J. C. (1992) · Neural Computation · doi:10.1162/neco.1992.4.3.448 · Cited by 2,917 · cited 1×
“In calculating V ( x , x (cid:48) ) def = E u [ h ( x ; u ) h ( x (cid:48) ; u ) ] we make the usual assumptions(MacKay,1992)that u isdrawnfromazero-meangaussiandistribution with covariance matrix (cid:54) , that is, u ∼ N ( 0 , (cid:54)) .”
BackgroundParzen, E. (1999) · doi:10.1137/1.9781611971125 · Cited by 1,389
Research works printed but not linked: 5
- Broomhead D., 1988, Complex Systems, 2, 321
- 10.2307/1268982 · doi:10.2307/1268982
- 10.1162/neco.1995.7.2.219 · DOI · Paper page
- 10.1016/S0893-6080(09)80018-X · DOI · Paper page
- 10.1109/5.58326 · DOI · Paper page
Cited by
Gaussian Processes for Machine Learning
Rasmussen, C. E., & Williams, C. K. I. (2005) · doi:10.7551/mitpress/3206.001.0001 · Cited by 11,705
“For example if we choose the error function h(z) = erf(z) = neural network covariance function 2/ √ π ∫ z 0 e−t 2 dt as the transfer function, let h(x;u) = erf(u0 + ∑D j=1ujxj) and choose u ∼ N (0,Σ) then we obtain [Williams, 1998]”
InfluentialSelf-citationGAUSSIAN PROCESSES FOR MACHINE LEARNING
SEEGER, M. (2004) · International Journal of Neural Systems · doi:10.1142/s0129065704001899 · Cited by 1,488
Bayesian classification with Gaussian processes
Williams, C. K. I., & Barber, D. (1998) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.735807 · Cited by 766
Self-citationPrediction with Gaussian Processes: From Linear Regression to Linear Prediction and Beyond
Williams, C. K. I. (1998) · Learning in Graphical Models · doi:10.1007/978-94-011-5014-9_23 · Cited by 659
Self-citationTresp, V. (2000) · Neural Computation · doi:10.1162/089976600300014908 · Cited by 402
Metadata
- Authors
- Williams, C. K. I.
- Venue
- Neural Computation
- Publisher
- MIT Press - Journals
- Published
- 1998-07-01
- Volume
- 10
- Issue
- 5
- Pages
- 1203-1216
- ISSN
- 0899-7667 (ISSN-L)
- 1530-888X
- OpenAlex
- W2072555316
- Cited by
- 149
- References
- 2
- FWCI
- 3.94
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Computation with Infinite Neural Networks. https://app.cochat.ai/papers/10.1162/089976698300017412
- The paper
- Williams, C. K. I. (1998). Computation with Infinite Neural Networks. Neural Computation. https://doi.org/10.1162/089976698300017412
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.