Controlled accuracy approximation of sigmoid function for efficient FPGA‐based implementation of artificial neurons. Issue 25 (1st December 2013)

• Record Type: Journal Article
• Authors: del Campo, I.; Finker, R.; Echanobe, J.; Basterretxea, K.
• Is Part Of: Electronics letters. Volume 49:Issue 25(2013)
• Page Start: 1598
• Page End: 1600
• Publication Date: 2013-12-01
• Subjects: approximation theory -- field programmable gate arrays -- learning (artificial intelligence) -- neural nets; sigmoid function -- FPGA‐based artificial neuron implementation -- controlled accuracy approximation scheme -- Taylor theorem -- Lagrange error form -- linear neuron part circuitry -- sigmoid derivative -- artificial neural networks -- online learning capabilities; Electronics -- Periodicals; 621.381
• DOI: 10.1049/el.2013.3098
• Languages: English
• ISSNs: 0013-5194

Abstract

Abstract : A controlled accuracy approximation scheme of the sigmoid function for artificial neuron implementation based on Taylor's theorem and the Lagrange form of the error is proposed. The main advantages of the proposed solution are two: it provides a systematic way to guarantee the required accuracy and it reuses the circuitry of the linear part of the neuron to compute the sigmoid function. The sigmoid derivative is also available for artificial neural networks with online learning capabilities.