FULLY DIGITAL ARTIFICIAL NEURON HARDWARE
Journal: Science and world (Vol.1, No. 9)Publication Date: 2014-05-23
Authors : Grigoryants V.P.; Petrosyan O.H.; Karapetyan G.A.;
Page : 99-109
Keywords : Artificial neuron; model; hardware; multiplexor; learning algorithm; simulation; layout; CMOS.;
- HYDRATION OF "HEADS" OF THE MYOSIN AND WORK OF SMOOTH MUSCLES
- ON THE HYDRATION ROLE IN WORK OF SMOOTH MUSCLES
- NANOSIZED TITANIUM DIOXIDE MATERIAL. MODULATION OF SPONTANEOUS MOTILITY AND GABA-DEPENDENT REGULATION OF FUNCTIONS OF STOMACH SMOOTH MUSCLES IN VIVO
- Hydration Matters, Role Of Body Hydration In Pain Control During Endodontic Therapy
- Effect of Hydration Education on College Athlete's Hydration Status and KAP
Abstract
Analysis of artificial neuron models is performed for hardware implementation. A method of synthesis polynomial threshold gate is suggested, which gives optimal values of weights and threshold in terms of hardware implementation. New paradigm of understanding artificial neuron as a logic gate is developed, which helps to implement artificial neuron hardware by multiplexor. This kind of model for artificial neuron has a lot of advantages over the known ones in terms of hardware implementation. Supervised learning algorithm is developed for multiplexor based neuron, which is simpler compared with the known learning algorithms, and also conversion from threshold neuron model to multiplexor neuron model is developed, which helps to use the known learning algorithms for developed neuron model. Finally multiplexors with 3 different structures is developed in 28nm technology and simulated over PVT by HSPICE, as well as comparison between them is performed.
Other Latest Articles
Last modified: 2015-08-11 18:47:59