论文信息 - Low Voltage-Power-Area FGMOS Neural Classifier Circuit for VLSI Analog BIST

Low Voltage-Power-Area FGMOS Neural Classifier Circuit for VLSI Analog BIST

This paper presents a novel Neural Classifier using FGMOS (Floating Gate MOSFET) . Basic reason for using FGMOS in Neural Classifier instead of classical MOSFET based Neural Classifier is to get significant reduction in area and power. Additional advantage of FGMOS based Neural Classifier is the simple circuitry as compared to classical MOSFET based Neural Classifier. 51.037% reduction in area is achieved in FGMOS based Neural Classifier (in .12μm technology). Along with this Neural classifier, 100 synapse and 10 Neurons reconfigurable network also implemented. KeywordsFGMOS, Synapse, Neuron, Reconfigurable Network, Floating Gate.

Priyanka Sharma | Kavita Khare | Ganesh Lakshmana Kumar.M

[1] Esther. Rodriguez-Villegas,et al. Low power and low voltage circuit design with the FGMOS transistor , 2006 .

[2] Ronald S. Gyurcsik,et al. Toward a general-purpose analog VLSI neural network with on-chip learning , 1997, IEEE Trans. Neural Networks.

[3] H. C. Card,et al. Analog CMOS deterministic Boltzmann circuits , 1993 .

[4] Yiorgos Makris,et al. An analog VLSI multilayer perceptron and its application towards built-in self-test in analog circuits , 2010, 2010 IEEE 16th International On-Line Testing Symposium.

[5] Gert Cauwenberghs. A Learning Analog Neural Network Chip with Continuous-Time Recurrent Dynamics , 1993, NIPS.

[6] S. Tam,et al. An electrically trainable artificial neural network (ETANN) with 10240 'floating gate' synapses , 1990, International 1989 Joint Conference on Neural Networks.