The DOI matches its Crossref record; the references it cites are not checked yet.
Using GPUs for machine learning algorithms
Abstract
Using dedicated hardware to do machine learning typically ends up in disaster because of cost, obsolescence, and poor software. The popularization of graphic processing units (GPUs), which are now available on every PC, provides an attractive alternative. We propose a generic 2-layer fully connected neural network GPU implementation which yields over 3/spl times/ speedup for both training and testing with respect to a 3 GHz P4 CPU.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
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?
GPUs are highly adaptable and efficient hardware for big datasets and are widely used in ML.
“GPUs are a highly adaptable and efficient hardware for big datasets and are widely used in ML fields (Steinkraus et al. 2005).”
From A Semi-Supervised Learning Method for the Identification of Bad Exposures in Large Imaging Surveys (2026) · cites this paper as Steinkraus et al. 2005
The insight of using GPUs to train ML models has been around for at least 7 years prior to AlexNet, and the utility for large-scale ML models is spelled out as early as 2005.
“The insight of using GPUs to train ML models has been around for at least 7 years prior to AlexNet, and the utility for large-scale ML models is spelled out as early as 2005 (Steinkraus et al., 2005).”
From Compute Trends Across Three Eras of Machine Learning (2022) · cites this paper as Steinkraus et al., 2005
Citations
The citation lists haven’t been fetched yet
References 8 · Cited by 251
Metadata
- Authors
- Steinkraus, D., Buck, I., & Simard, P. Y.
- Affiliations
- Microsoft (United States) (US)
- Stanford University (US)
- Venue
- Eighth International Conference on Document Analysis and Recognition (ICDAR'05)
- Publisher
- IEEE
- Published
- 2005
- Pages
- 1115-1120 Vol. 2
- ISSN
- 1520-5363 (ISSN-L)
- OpenAlex
- W2071039340
- Cited by
- 251
- References
- 8
- Citations by year
- 2026: 3 · 2025: 13 · 2024: 21 · 2023: 23 · 2022: 28 · 2021: 20 · 2020: 28 · 2019: 27 · 2018: 17 · 2017: 8 · 2016: 9 · 2015: 8 · 2014: 7 · 2013: 4 · 2012: 6
- FWCI
- 0.71
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IAPR International Conference on Document Analysis and Recognition (ICDAR) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Hardware and Architecture › Parallel Computing and Optimization Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- GPU acceleration, machine learning hardware, fully connected neural network, neural network training, neural network inference, speedup, CPU vs GPU performance comparison
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
