Prototyping of WTA ANNs using FPAA devices

A rapid prototyping method for designing a winner takes all (WTA) artificial neural networks (ANNs) has been presented in the paper. The method is based on implementation of field programmable analog arrays (FPAAs) to design WTA ANNs. Programmable synaptic weight connection circuit and 2-WTA circuit are proposed. The 2-WTA circuits are used to configure 4-WTA and 8-WTA circuits. 4-WTA and 8-WTA circuits and programmable synaptic weight connection circuit have been implemented in FPAA device, simulated with a help of the Matlab software and finally measured. Measured characteristics have been compared to simulated ones.

[1]  Marcelo Lubaszewski,et al.  Applying the Oscillation Test Strategy to FPAA’s Configurable Analog Blocks , 2005, J. Electron. Test..

[2]  Bing J. Sheu,et al.  A high-precision VLSI winner-take-all circuit for self-organizing neural networks , 1993 .

[3]  Sarma Vrudhula,et al.  Programmable Analog/Digital Arrays in Control and Simulation , 2004 .

[4]  Robert Suszynski,et al.  Rapid prototyping of algorithmic A/D converters based on FPAA devices , 2013 .

[5]  V. A. Pedroni.  Inhibitory mechanism analysis of complexity O(N) MOS winner-take-all networks , 1995 .

[6]  K. Wawryn,et al.  Prototyping of higher order ΣΔ ADC based on implementation of a FPAA , 2012, 2012 International Conference on Signals and Electronic Systems (ICSES).

[7]  Jun Wang,et al.  Information retrieval from large data sets via multiple-winners-take-all , 2011, 2011 IEEE International Symposium of Circuits and Systems (ISCAS).

[8]  Witold Pedrycz,et al.  Realization of the Conscience Mechanism in CMOS Implementation of Winner-Takes-All Self-Organizing Neural Networks , 2010, IEEE Transactions on Neural Networks.

[9]  Edgar Sanchez-Sinencio,et al.  Min-net winner-take-all CMOS implementation , 1993 .

[10]  Helmy Widyantara.  Implementation Analog Neural Network for Electronic Nose using Field Programable Analog Arrays (FPAA) , 2012 .

[11]  Qingshan Liu,et al.  A Novel Recurrent Neural Network with a Continuous Activation Function for Winner-Take-All , 2013, 2013 4th International Conference on Intelligent Systems, Modelling and Simulation.

[12]  John Taylor,et al.  A scalable high-speed current-mode winner-take-all network for VLSI neural applications , 1995 .