Analog-Counter-Based Conscience Mechanism in Kohonen's Neural Network Implemented in CMOS 0.18 μm Technology

Tomasz Talaska; Ryszard Wojtyna; Rafal Dlugosz; Krzysztof Iniewski; Witold Pedrycz; IEEE

doi:10.1109/SIPS.2006.352619

Back

Conference proceeding

Analog-Counter-Based Conscience Mechanism in Kohonen's Neural Network Implemented in CMOS 0.18 μm Technology

Tomasz Talaska, Ryszard Wojtyna, Rafal Dlugosz, Krzysztof Iniewski, Witold Pedrycz and IEEE

2006 IEEE Workshop on Signal Processing Systems Design and Implementation, pp.416-421

10/2006

DOI: https://doi.org/10.1109/SIPS.2006.352619

Abstract

Agriculture

CMOS technology

Counting circuits

Fellows

Microelectronics

Neural networks

Neurons

Self organizing feature maps

Technology management

Telecommunications

In this study, we present a hardware implementation of the conscience mechanism in Kohonen self-organizing maps. The proposed realization of the conscience mechanism is important to the functioning of the neural network as it eliminates so-called dead (inactive) neurons. As a result the network learning, the level quantization error can be reduced. The conscience mechanism and the Winner Take All (WTA) block have been implemented in 0.18 μm CMOS process. The implementation of the conscience mechanism itself occupies 1200 μm 2 and its maximum power consumption is 9.5 μW. The WTA block together with the conscience mechanism occupies 0.024 mm 2 and dissipates 55 μ W

Metrics

1 Record Views

Details

Title: Analog-Counter-Based Conscience Mechanism in Kohonen's Neural Network Implemented in CMOS 0.18 μm Technology
Creators - without role: Tomasz Talaska - Bydgoszcz University of Science and Technology
Ryszard Wojtyna - Bydgoszcz University of Science and Technology
Rafal Dlugosz - Foundation for Polish Science
Krzysztof Iniewski - University of Alberta
Witold Pedrycz - University of Alberta
IEEE
Publication Details: 2006 IEEE Workshop on Signal Processing Systems Design and Implementation, pp.416-421
Publisher: IEEE
Identifiers: 9934754708331
Academic Unit: King Abdulaziz University
Language: English
Resource Type: Conference proceeding