How to keep the HG weights non-negative: the truncated Perceptron reweighing rule
How to keep the HG weights non-negative: the truncated Perceptron reweighing rule
复制标题
如何保持 HG 权重非负：截断感知器重新加权规则
DOI：
--
复制
发表时间：
2015
影响因子：
--
通讯作者：
Giorgio Magri
中科院分区：
文献类型：
--
作者：
Giorgio Magri
谐波语法（HG）中关于错误驱动学习的文献采用了感知器重新加权规则。然而，这条规则并不适合 HG，因为它无法确保非负权重。因此考虑一种变体，它将更新截断为零，保持权重非负。原始感知器的收敛保证和误差范围被证明可以扩展到其截断的变体。
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.