| ROA: | 1268 |
| Title: | How to keep the HG weights non-negative: the truncated Perceptron reweighing rule |
| Authors: | Giorgio Magri |
| Comment: | to appear in the Journal of Language Modelling |
| Length: | 32 |
| Abstract: | The literature on error-driven learning in Harmonic Grammar (HG) has adopted the Perceptron reweighing rule. Yet, this rule is not suited to HG, as it fails at ensuring non-negative weights. A variant is thus considered which truncates the updates at zero, keeping the weights non-negative. Convergence guarantees and error bounds for the original Perceptron are shown to extend to its truncated variant. |
| Type: | Paper/tech report |
| Area/Keywords: | learnability, error-driven learning, HG, Perceptron |
| Article: | Version 1
|
