Optical neural network: architecture design and models

摘要

Abstract: An adaptive optical neuro network using inexpensive pocket size liquid crystal televisions (LCTVs) was recently developed by graduate students in the Electro-Optics Laboratory at The Pennsylvania State University. Although this neuro-computing has only 8 $MUL 8 $EQ 64 neurons, it can be easily extended to 16 $MUL 20 $EQ 320 neurons. The major advantages of this LCTV architecture as compared wither other ONCs, are low cost and flexibility to operate. To test the performance, several neural net models are used. These models are interpattern association, hetero-association, and unsupervised learning algorithms. The system design considerations and experimental demonstrations are also included.!12