We describe the design and successful operation of an optoelectronic Hopfield network demonstrator system. The Hopfield network, one of the simpler space-invariant interneuronal connection networks, was chosen due to its observed efficiency in solving optimization tasks. The demonstrator system, based around a free-space diffractive optical interconnect, was designed to perform a range of optimization tasks, in particular those associated with the scheduling of packets through different switching topologies. Experimental optimization of the neural network throughput, for both a crossbar and Banyan switch topology, allows the neural network parameters (e.g., neuron bias, neuron weighting) to be tuned to ensure optimal operation of the network for a particular switch topology. In addition, the demonstrator allows an investigation of the critical parameters governing the interoperation of the different modules. In this paper, we describe the effect of two of these parameters, namely, the operating temperature of the optoelectronic devices and the accuracy of the interconnection fabrication technology. The weighted interconnections in this optoelectronic system are provided by a diffractive optical element/lens combination whilst the neurons are implemented electronically. The transition between the electronic and optical domains is handled by an 8/spl times/8 VCSEL array for the electronic-optic interface, and an 8/spl times/8 Si photodetector array for the optic-electronic interface. The VCSEL array consists of oxide-confined near-infrared GaAs devices capable of 250-MHz modulation at a wavelength of 960 nm. The diffractive optical interconnect is designed using simulated annealing optimization and fabricated using very large scale integration photolithography. Using these techniques, it is possible to create interconnects with a total efficiency of /spl sim/70% and a nonuniformity of <1%.

Experimental implementation of an optoelectronic neural network scheduler

Reviewed the technologies behind two successful optoelectronic demonstrator systems. These demonstrators show that the optics-in-computing technologies are reaching a level of sophistication where their deployment in "real-world" computing/networking environments becomes increasingly likely. The primary requirements for the successful transfer of these technologies from the laboratory to the "real world" are larger, more uniform arrays of the optoelectronic devices and highly stable optical and optomechanical assemblies. The advent of high-efficiency, low-power consumption arrays of oxide-confined VCSELs has reduced the overall optical complexity of these demonstrators with subsequent gains in the mechanical stability of these optical systems. Although at present the maximum array size of VCSELs that is readily available is 8 /spl times/ 8, there is, in principle, no reason why larger arrays cannot be developed. In tandem with these developments, the design and fabrication of micro-optical elements has reached the stage where they can be regarded as the standard optoelectronic interconnection method. Micro-optical optoelectronic system demonstrators show that optics-in-computing interconnection technologies are nearing real-world readiness.

Demonstrating a bright future [optoelectronic demonstrators]

In this paper we shall describe the design and successful operation of an optoelectronic Hopfield network demonstrator system. This demonstrator system, based around a free-space diffractive optical interconnect, was designed to perform a range of optimisation tasks, in particular those associated with the scheduling of packets through different switching topologies. Experimental optimisation of the neural network throughput, for both a crossbar and Banyan switch topology, allows the neural network parameters (e.g. neuron bias, neuron weighting) to be tuned to ensure optimal operation of the network for a particular switch topology. The weighted interconnections in this optoelectronic system are provided by a diffractive optical element/lens combination whilst the neurons are implemented electronically. The transition between the electronic and optical domains is handled by an 8×8 VCSEL array for the electronic-optic interface, and an 8×8 Si photodetector array for the optic-electronic interface. The VCSEL array, supplied by Avalon Photonics, is an oxide-confined near-infrared GaAs device capable of 250MHz modulation at a wavelength of 960nm. The diffractive optical interconnect is designed using simulated annealing optimization and fabricated using VLSI photolithography. Using these techniques it is possible to create interconnects with a total efficiency of ~70% and a uniformity of < 1%.

VCSEL operational requirements for optoelectronic neural networks

The continuing improvement in micron-scale optical element design and fabrication has driven the creation of ever more complex optics-in-computing system demonstrators. In this paper we shall review two such demonstrators and discuss the flexibility of the micro-optical approach.

A.J. Waddie

Papers

Micro-optical elements and optoelectronic devices in optics-in-computing system demonstrators