Persistent Spectral Hole Burning Applications for Massive Optical Neural Network Computers,
Abstract
Neural networks require two types of operations; interconnections, which define how the output of one state affects the input of the next, and non-linear operations, which relate the inputs of a state to its output. Interconnections, which require many signals passing through the same space, are best performed with photons, which do not interact with one another. Non-linear operations require interaction (i.e., cross products) between the various inputs to a state, and are best performed with electrons, which interact strongly through their electrical charge. In a typical neural network architecture, almost all of the computation required is associated with the interconnections, and only a tiny fraction is associated with the non-linear operations (sigmoidal response or thresholding) performed at each state. In this paper we will present an architecture which uses both photons and electrons in a natural manner to perform all the functions required for a complete neural network architecture. A schematic of this architecture is shown in Figure 1. Almost all of the computations are performed optically in parallel, providing the capability to implement extremely large neural networks.
Document Details
- Document Type
- Technical Report
- Publication Date
- May 22, 1992
- Accession Number
- ADP008236
Entities
People
- Philip D. Henshaw
- Steven A. Lis