Title :
Multi-input silicon neuron with weighting adaptation
Author :
Li, Ming-Ze ; Ping-Wang, Po ; Tang, Kea-Tiong ; Fang, Wai-Chi
Author_Institution :
Dept. of Electr. Eng., Nat. Tsing Hua Univ., Hsinchu
Abstract :
This paper presents a biologically inspired ldquointegrate-and-fire (I&F) neuronrdquo which has multiple input dendrites for adaptive weight storage. By using a capacitor-free integrator, longer time constant and smaller chip area can be achieved. A low-power Schmitt Trigger is used to implement the feedback loop to achieve smaller power consumption. Weights are stored by using floating gate MOS transistors as nonvolatile analog memory. Simulation results show that this I&F neuron can be utilized in an analog VLSI neural network system.
Keywords :
MOSFET; VLSI; neural nets; neurophysiology; silicon; trigger circuits; adaptive weight storage; analog VLSI neural network system; biologically inspired integrate-and-fire neuron; capacitor-free integrator; feedback loop; floating gate MOS transistor; low-power Schmitt trigger; multi-input silicon neuron; multiple input dendrites; nonvolatile analog memory; Analog memory; Energy consumption; Feedback loop; MOSFETs; Neural networks; Neurons; Nonvolatile memory; Silicon; Trigger circuits; Very large scale integration;
Conference_Titel :
Life Science Systems and Applications Workshop, 2009. LiSSA 2009. IEEE/NIH
Conference_Location :
Bethesda, MD
Print_ISBN :
978-1-4244-4292-8
Electronic_ISBN :
978-1-4244-4293-5
DOI :
10.1109/LISSA.2009.4906744