#### Technical Report USC-SIPI-307

“Scalable Photonic Neural Networks for Real-Time Pattern Classification”

by Adam A. Goldstein

May 1997

With the rapid advancement of photonic technology in recent years, the potential exists for the incorporation of photonic neural-network research into the development of opto-electronic real-time pattern classification systems. In this dissertation we present three classes of photonic neural-network models that were designed to be compatible with this emerging technology: (1) photonic neural networks based upon probability density estimation, (2) photorefractive neural-network models, and (3) vertically stacked photonic neural networks that utilize hybridized CMOS/GaAs chips and diffractive optical elements. In each case, we show how previously developed neural-network learning algorithms and/or architectures must be adapted in order to allow an efficient photonic implementation.

For class (1), we show that conventional "k-Nearest Neighbors'' (k-NN) probability density estimation is not suitable for an analog photonic neural-network hardware implementation, and we introduce a new probability density estimation algorithm called "Continuous k-Nearest Neighbors'' (C-kNN) that is suitable. For class (2), we show that the diffraction-efficiency decay inherent to photorefractive grating formation adversely affects outer-product neural-network learning algorithms, and we introduce a gain and exposure scheduling technique that resolves the incompatibility. For class (3), the use of compact diffractive optical interconnections constrains the corresponding neural-network weights to be fixed and locally connected. We introduce a 3-D Photonic Multichip-Module (3-D PMCM) neural-network architecture that utilizes a fixed diffractive optical layer in conjunction with a programmable electronic layer, to obtain a multi-layer neural network capable of real-time pattern recognition tasks. The design and fabrication of key components of the 3-D PMCM neural-network architecture are presented, together with simulation results for the application of detecting and locating the eyes in an image of a human face.

#### To download the report in PDF format click here: USC-SIPI-307.pdf (32.2Mb)