Conditions on abruptness in a gradient-ascent Maximum Entropy learner
Conditions on abruptness in a gradient-ascent Maximum Entropy learner
复制标题
DOI：
10.7275/r5xg9pbx
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
E. Moreton
中科院分区：
文献类型：
--
作者：
E. Moreton
渐进式学习规则何时转化为渐进式学习绩效？本文研究了梯度上升最大熵语音定向学习器，并将其应用于以对数优势表示的两种选择性强迫选择。主要结果是，如果初始权重接近于零，则缓慢的初始性能不能在以后加速，但如果初始权重不接近于零，则可以加速。换句话说，这个学习者的不熟练是一种迁移的结果，要么是以初始权重的形式来自普遍语法，要么是以习得权重的形式来自先前的学习。
When does a gradual learning rule translate into gradual learning performance? This paper studies a gradient-ascent Maximum Entropy phonotactic learner, as applied to twoalternative forced-choice performance expressed as log-odds. The main result is that slow initial performance cannot accelerate later if the initial weights are near zero, but can if they are not. Stated another way, abruptness in this learner is an effect of transfer, either from Universal Grammar in the form of an initial weighting, or from previous learning in the form of an acquired weighting.