Size invariance does not hold for connectionist models: dangers of using a toy model
Size invariance does not hold for connectionist models: dangers of using a toy model
复制标题
尺寸不变性不适用于联结主义模型：使用玩具模型的危险
作者：
M. Yamaguchi
众所周知，具有反向传播学习规则的连接主义模型存在称为灾难性干扰或遗忘的严重问题，尽管已有多个报告表明，对于正交输入，干扰可能相对较小。本研究调查了具有不同网络规模的正交输入的干扰程度。人们自然会认为，从小型网络获得的结果可以外推到大型网络。出乎意料的是，使用小型网络会降低性能。这一结果对解释文献中的一些数据具有重要意义，并警告不要使用玩具模型。
Connectionist models with backpropagation learning rule are known to have a serious problem called catastrophic interference or forgetting, although there have been several reports showing that the interference can be relatively mild with orthogonal inputs. The present study investigated the extent of interference using orthogonal inputs with varying network sizes. One would naturally assume that results obtained from small networks could be extrapolated for larger networks. Unexpectedly, the use of small networks was shown to worsen performance. This result has important implications for interpreting some data in the literature and cautions against the use of a toy model.
影响因子：
5.4
作者：
RATCLIFF, R
通讯作者：
RATCLIFF, R