Implementing Recurrent Back Propagation on the Connection Machine. Final report
Technical Report
·
OSTI ID:6062943
Pineda's Recurrent Back-Propagation algorithm for neural networks was implemented on the Connection Machine, a massively parallel processor. Two fundamentally different graph architectures underlying the nets were tested - one based on arcs, the other on nodes. Confirming the predominance of communication over computation, performance measurements underscore the necessity to make connections the basic unit of representation. Comparisons between these graphs algorithms lead to important conclusions concerning the parallel implementation of neural nets in both software and hardware.
- Research Organization:
- Naval Research Lab., Washington, DC (USA)
- OSTI ID:
- 6062943
- Report Number(s):
- AD-A-203796/8/XAB; NRL-9167
- Country of Publication:
- United States
- Language:
- English
Similar Records
Back propagation parameter analysis on multiprocessors
Data-driven data base model and its implementation on a highly-parallel architecture
Numerical computation on massively parallel hypercubes. [Connection machine]
Conference
·
Thu Sep 01 00:00:00 EDT 1988
· Neural Networks; (United States)
·
OSTI ID:6062943
Data-driven data base model and its implementation on a highly-parallel architecture
Thesis/Dissertation
·
Thu Jan 01 00:00:00 EST 1987
·
OSTI ID:6062943
Numerical computation on massively parallel hypercubes. [Connection machine]
Conference
·
Wed Jan 01 00:00:00 EST 1986
·
OSTI ID:6062943