Abstract
Results are reported on the task of recognizing handwritten digits without any advanced pre-processing. The result are obtained using a RAM-based neural network, making use of small receptive fields. Furthermore, a technique that introduces negative weights into the RAM net is reported. The results obtained on the task of recognizing handwritten digits is comparable with the best performances reported in the literature.
Original language | English |
---|---|
Journal | International Journal of Neural Systems |
Volume | 8 |
Issue number | 1 |
Pages (from-to) | 17-25 |
ISSN | 0129-0657 |
DOIs | |
Publication status | Published - Feb 1997 |
Event | 2nd International Conference on Engineering Applications of Neural Networks - London, United Kingdom Duration: 17 Jun 1996 → 19 Jun 1996 Conference number: 2 |
Conference
Conference | 2nd International Conference on Engineering Applications of Neural Networks |
---|---|
Number | 2 |
Country/Territory | United Kingdom |
City | London |
Period | 17/06/1996 → 19/06/1996 |