Boosting neural network feature extraction by reduced accuracy activation functions
✍ Scribed by A. Raudys
- Book ID
- 104161648
- Publisher
- Elsevier Science
- Year
- 2003
- Tongue
- English
- Weight
- 362 KB
- Volume
- 36
- Category
- Article
- ISSN
- 0031-3203
No coin nor oath required. For personal study only.
✦ Synopsis
The paper proposes the use of a lookup table in the computation of the sigmoid function in multilayer perceptron feature extraction. The approach is frequently used in limited precision hardware implementations. This paper considers its use as a software implementation. It is argued that the method is computationally e cient and does not compromise the performance of the neural networks. This new approach is analysed and evaluated in both theoretical and experimental terms. The practical study is performed using several real world and synthetic data sets. The results show that an increase in computational e ciency is achieved with very little or no in uence on the quality of the extracted features.