Adaptive resonance theory networks using incremental communication
| dc.contributor.author | Chen, Ming | |
| dc.contributor.author | Ghorbani, Ali, A. | |
| dc.contributor.author | Bhavsar, Virendra, C. | |
| dc.date.accessioned | 2023-03-01T18:30:02Z | |
| dc.date.available | 2023-03-01T18:30:02Z | |
| dc.description.abstract | The incremental inter-node communication method is applied to the adaptive resonance theory 2 (ART2) networks. The incremental communication is aimed at reducing the communication costs of parallel and VLSI implementations of artificial neural networks. A node architecture incorporating the incremental communication is presented. A simulator is developed to stndy the behavior of ART2 networks with varying precisions of incremental data communication. Experiments are carried out to study the effects of the incremental communication on the convergence and savings in communication costs. We have found that even 7-bit precision in fixed-point and 13-bit (including 8-bit exponent) floating-point representations may be sufficient for the network to give the same results as those with conventional communication using 32-bit precision. The simulation results show that the limited precision errors are bounded and do not seriously affect the convergence of ART2 networks. | |
| dc.description.copyright | Copyright @ Ming Chen, Ali A. Ghorbani, and Virendra C. Bhavsar. | |
| dc.identifier.uri | https://unbscholar.lib.unb.ca/handle/1882/14967 | |
| dc.rights | http://purl.org/coar/access_right/c_abf2 | |
| dc.subject.discipline | Computer Science | |
| dc.title | Adaptive resonance theory networks using incremental communication | |
| dc.type | technical report |
Files
Original bundle
1 - 1 of 1