Compressive Elm: Improved Models through Exploiting Time-Accuracy Trade-Offs
Abstract
In the Training of Neural Networks, There Often Exists a Trade-Off between the Time Spent Optimizing the Model under Investigation, and its Final Performance. Ideally, an Optimization Algorithm Finds the Model that Has Best Test Accuracy from the Hypothesis Space as Fast as Possible, and This Model is Efficient to Evaluate at Test Time as Well. However, in Practice, There Exists a Trade-Off between Training Time, Testing Time and Testing Accuracy, and the Optimal Trade-Off Depends on the User's Requirements. This Paper Proposes the Compressive Extreme Learning Machine, Which Allows for a Time-Accuracy Trade-Off by Training the Model in a Reduced Space. Experiments Indicate that This Trade-Off is Efficient in the Sense that on Average More Time Can Be Saved Than Accuracy Lost. Therefore, It Provides a Mechanism that Can Yield Better Models in Less Time. © Springer International Publishing Switzerland 2014.
Recommended Citation
M. van Heeswijk et al., "Compressive Elm: Improved Models through Exploiting Time-Accuracy Trade-Offs," Communications in Computer and Information Science, vol. 459 CCIS, pp. 165 - 174, Springer, Jan 2014.
The definitive version is available at https://doi.org/10.1007/978-3-319-11071-4_16
Department(s)
Engineering Management and Systems Engineering
Keywords and Phrases
approximate matrix decompositions; compressive sensing; ELM; Extreme Learning Machine; Johnson-Lindenstrauss; random projection
International Standard Book Number (ISBN)
978-331911070-7
International Standard Serial Number (ISSN)
1865-0929
Document Type
Article - Conference proceedings
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2024 Springer, All rights reserved.
Publication Date
01 Jan 2014
