7.5.10 Computation- and Memory-Based Projective Field Processors

Participants: K. Boahen, A. Andreou, T. Hinck, J. Kramer, A. Whatley
    We investigated two ways to extend the point-to-point address-event communication
channel to include divergent (point-to-many) and convergent (many-to-point) connections
at this workshop.  The first approach uses integer arithmetic to compute the destination
addresses.  This computation-intensive approach is tailored towards arrays with translation-
invariant receptive fields, where corresponding projective fields may be computed simply
by adding the same set of offsets to each incoming address-event.  The second approach
uses look-up tables to obtain the destination addresses.  This memory-intensive approach is
tailored towards arrays with space-variant receptive fields, where the connectivity changes
in a way that is difficult to compute.  We had prototype systems that used both of these
approaches at the workshop, and we experimented with these systems, and compared their
performance and ease of use.
    The first system had three 64x64-neuron AER receiver chips and six 8-bit microcon-
trollers (MicroChip PIC16C55).  These microcontrollers work in parallel, with one pair
computing the X and Y addresses for each receiver chip.  The throughput was 3M addresses
per second; this rate supports an incoming address-event rate of 83K with a fan-out of 5.
This system was rather slow because the microcontrollers operated at only 5MIPS, and
about 10 instructions where executed to perform the handshaking protocol and to add the
offset to the address.  The system was also difficult to use, as we had to modify programs
written in assembly language to implement new projective fields.
The second system had four 64x64-neuron AER receiver chips and five 64k X 16 EPROM
chips.  However, this prototype only supported a single outgoing address per receiver chip
for each incoming address.  We designed and started building a memory-based system that
supported projective fields at the workshop.  The new design uses an EEPROM to store
the projective field mapping and a microcontroller to perform the handshake protocols
and to sequence through several locations in the EEPROM for each incoming address.
We completed the program for the microcontroller as well as the address mapping for the
EEPROM.  Further debugging of the hardware and software will continue between Hopkins
and Boston University.