Accession Number : ADA299796

Title :   Reinforcement Learning Neural Networks for Optical Communications.

Descriptive Note : Quarterly rept. 2 Jan-2 Apr 95,

Corporate Author : TACAN CORP CARLSBAD CA

Personal Author(s) : Salour, Michael

PDF Url : ADA299796

Report Date : 02 APR 1995

Pagination or Media Count : 5

Abstract : The objective of this work is to utilize neural networks to find new methods for optimizing high performance fiber-optic communication links. In typical broadband analog optical communication links, the dominant distortion comes from the transmitter. The electrical-to-optical transfer characteristics of both electro-optic external modulators and semiconductor lasers are nonlinear and create both odd and even-order harmonic distortions of the modulating signal. One cost-effective method to cancel device non-linearities in direct modulated lasers is by electronic predistortion. For our previous work, based on the simulated annealing learning algorithm utilized for neural network learning, a novel algorithm was developed to obtain the initial parameters of predistortion and laser circuits, and it has been used to linearize the Distributed FeedBack (DFB) semiconductor laser transmitters.

Descriptors :   *NEURAL NETS, *OPTICAL COMMUNICATIONS, ALGORITHMS, SIMULATION, OPTICAL PROPERTIES, OPTIMIZATION, COST EFFECTIVENESS, ELECTROOPTICS, MONITORING, SEMICONDUCTOR LASERS, LASERS, DRIFT, FEEDBACK, SIGNALS, LINEARITY, TRANSMITTERS, EXTERNAL, POWER, CIRCUITS, TRANSFER, MODULATION, BIAS, LEARNING, DISTORTION, MODULATORS, LASER COMPONENTS, DISTRIBUTED AMPLIFIERS.

Subject Categories : Electrooptical and Optoelectronic Devices
      Cybernetics
      Telemetry

Distribution Statement : APPROVED FOR PUBLIC RELEASE