The use of random weights for the training of multilayer networks of neurons with Heaviside characteristics
Open accessIntegrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Gradient descent has been achieved using Heaviside activation functions by taking the weights as Gaussian variables and taking partial derivatives with respect to the means and standard deviations.
“Nevertheless, gradient descent has also been achieved using Heaviside activation functions, by taking the weights as Gaussian variables and taking partial derivatives w.r.t. the means and standard deviations of the appropriate Gaussian distributions.33,34”
From Quantum generalisation of feedforward neural networks (2017) · cites this paper as [34]
Cites
Parallel Distributed Processing: Explorations in the Microstructure of Cognition: Foundations
Rumelhart, D. E., McClelland, J. L., & AU (1986) · doi:10.7551/mitpress/5236.001.0001 · Cited by 15,686 · see citing works
The perceptron: A probabilistic model for information storage and organization in the brain.
Rosenblatt, F. (1958) · Psychological Review · doi:10.1037/h0042519 · Cited by 12,280 · see citing works
McClelland, J. L., Rumelhart, D. E., & AU (1987) · doi:10.7551/mitpress/5237.001.0001 · Cited by 3,315 · see citing works
Advances in Neural Information Processing Systems 37
Touretzky, D. S. (2024) · doi:10.52202/079017 · Cited by 2,874 · see citing works
Nguyen, D., & Widrow, B. C. (1990) · 2022 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.1990.137819 · Cited by 1,386 · see citing works
Neural nets for adaptive filtering and adaptive pattern recognition
Widrow, B. C., & Winter, R. (1988) · Computer · doi:10.1109/2.29 · Cited by 470 · see citing works
Neural net pruning-why and how
Sietsma, & Dow (1988) · IEEE International Conference on Neural Networks/IEEE ... International Conference on Neural Networks · doi:10.1109/icnn.1988.23864 · Cited by 235 · see citing works
Accelerated learning in layered neural networks
Solla, S. A., Levin, E., & Fleisher, M. (1988) · Complex Systems · Cited by 210 · see citing works
Neural net pruning-why and how.
Sietsma, J., & Dow, R. J. F. (1988) · Cited by 193 · see citing works
The “moving targets” training algorithm
Rohwer, R. (1990) · Lecture notes in computer science · doi:10.1007/3-540-52255-7_31 · Cited by 47 · see citing works
Using random weights to train multilayer networks of hard-limiting units
Barlett, P. L., & Downs, T. (1992) · IEEE Transactions on Neural Networks · doi:10.1109/72.125861 · Cited by 40 · see citing works
Self-citationTraining binary node feedforward neural networks by back propagation of error
Toms, D. J. (1990) · Electronics Letters · doi:10.1049/el:19901121 · Cited by 34 · see citing works
A Cost Function for Internal Representations
Krogh, A., Thorbergsson, C. I., & Hertz, J. (1989) · neural information processing systems · Cited by 31 · see citing works
Sigmoids Distinguish More Efficiently Than Heavisides
Sontag, E. D. (1989) · Neural Computation · doi:10.1162/neco.1989.1.4.470 · Cited by 27 · see citing works
New 32-QAM trellis codes for fading channels
Du, J., Kamio, Y., Sasaoka, H., & Vucetic, B. S. (1993) · Electronics Letters · doi:10.1049/el:19931162 · Cited by 10 · see citing works
Learning in Feedforward Networks with Nonsmooth Functions
Redding, N. J., & Downs, T. (1991) · Cited by 3 · see citing works
Self-citation
Flagged first, then by citations
3 of the 19 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Quantum generalisation of feedforward neural networks
Wan, K. H., Dahlsten, O., Kristjánsson, H., Gardner, R., & Kim, M. S. (2017) · npj Quantum Information · doi:10.1038/s41534-017-0032-4 · Cited by 276 · see citing works
Noise-modulated neural networks as an application of stochastic resonance
Ikemoto, S., DallaLibera, F., & Hosoda, K. (2017) · Neurocomputing · doi:10.1016/j.neucom.2016.12.111 · Cited by 47 · see citing works
Ye, W., Lin, J., Zhang, X., Lian, Q., Liu, Y., Wang, H., Wu, S., Chen, H., & Guo, T. (2022) · Nano Energy · doi:10.1016/j.nanoen.2022.107525 · Cited by 41 · see citing works
Ikemoto, S. (2021) · Neurocomputing · doi:10.1016/j.neucom.2020.05.125 · Cited by 15 · see citing works
Ikemoto, S., Libera, F. D., & Hosoda, K. (2016) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2016.7727525
- Authors
- Downs, T., & Gaynier, R. J.
- Affiliations
- The University of Queensland (AU)
- Venue
- Mathematical and Computer Modelling
- Publisher
- Elsevier BV
- Published
- 1995-11
- Volume
- 22
- Issue
- 10-12
- Pages
- 53-61
- ISSN
- 0895-7177 (ISSN-L)
- OpenAlex
- W2033728239
- Cited by
- 5
- References
- 19
- Citations by year
- 2022: 1 · 2021: 1 · 2017: 2 · 2016: 1
- FWCI
- 0.00
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Licence
- Locations
- Mathematical and Computer Modelling (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and ELM
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Memory and Neural Computing
- Keywords
- random weights, multilayer neural networks, backpropagation, neural network training algorithms, internal representations
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
