The Differentiable Neural Computer (DNC) can learn algorithmic and question answering tasks. An analysis of its internal activation patterns reveals three problems: Most importantly, the lack of key-value separation makes the address distribution resulting from content-based look-up noisy and flat, since the value influences the score calculation, although only the key should. Second, DNC's de-allocation of memory results in aliasing, which is a problem for content-based look-up. Thirdly, chaining memory reads with the temporal linkage matrix exponentially degrades the quality of the address distribution. Our proposed fixes of these problems yield improved performance on arithmetic tasks, and also improve the mean error rate on the bAbI question answering dataset by 43%.
翻译:不同的神经计算机(DNC)可以学习算法和问题解答任务。对内部激活模式的分析揭示了三个问题:最重要的是,由于缺少关键值分离,使得基于内容的外观、杂乱和平板的地址分布变得平坦,因为价值影响评分的计算,尽管只有关键值。第二,DNC的内存脱位导致别名,这是基于内容的外观问题。第三,连锁内存与时间链接矩阵的读取会急剧降低地址分布的质量。我们提议的这些问题的解决方案提高了计算任务的业绩,也提高了BAbI问题中平均误差率43%的回答数据。