Academic Journal
Incremental learning with rulebased neural networks
| العنوان: | Incremental learning with rulebased neural networks |
|---|---|
| المؤلفون: | C. M. Higgins, R. M. Goodman |
| المساهمون: | The Pennsylvania State University CiteSeerX Archives |
| المصدر: | http://neuromorph.ece.arizona.edu/~higgins/pubs/oldpubs/ijcnn91.pdf. |
| سنة النشر: | 1991 |
| المجموعة: | CiteSeerX |
| الوصف: | A classi er for discrete-valued variable classi cation problems is presented. The system utilizes an information-theoretic algorithm for constructing informative rules from example data. These rules are then used to construct a neural network to perform parallel inference and posterior probability estimation. The network can be `grown ' incrementally, so that new data can be incorporated without repeating the training on previous data. It is shown that this technique performs comparably with other techniques such as back-propagation while having unique advantages in incremental learning capability, training e ciency, knowledge representation, and hardware implementation suitability. 1 |
| نوع الوثيقة: | text |
| وصف الملف: | application/pdf |
| اللغة: | English |
| Relation: | http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.71.983; http://neuromorph.ece.arizona.edu/~higgins/pubs/oldpubs/ijcnn91.pdf |
| الاتاحة: | http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.71.983 http://neuromorph.ece.arizona.edu/~higgins/pubs/oldpubs/ijcnn91.pdf |
| Rights: | Metadata may be used without restrictions as long as the oai identifier remains attached to it. |
| رقم الانضمام: | edsbas.4AD0F85E |
| قاعدة البيانات: | BASE |
| الوصف غير متاح. |