.png){kind=icon}
返回
Minimum Description Length Recurrent Neural Networks
.png){kind=icon}
OA
AI
DOI：10.1162/tacl_a_00489.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We train neural networks to optimize a Minimum Description Length score, that is, to balance between the complexity of the network and its accuracy at a task. We show that networks optimizing this objective function master tasks involving memory challenges and go beyond context-free languages. These learners master languages such as a(n)b(n), a(n)b(n)c(n), a(n)b(2n), a(n)b(m)c(n +m), and they perform addition. Moreover, they often do so with 100% accuracy. The networks are small, and their inner workings are transparent. We thus provide formal proofs that their perfect accuracy holds not only on a given test set, but for any input sequence. To our knowledge, no other connectionist model has been shown to capture the underlying grammars for these languages in full generality.
期刊
T
IF:
6.9
论文数:
486
被引数:
5.7K
机构
引用论文
Race, Ethnicity, Income Concentration and 10-Year Change in Urban Greenness in the United States
OAAI
OAAI分享收藏分享收藏Discovering neural nets with low Kolmogorov complexity and high generalization capability.png)
NEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
分享收藏
查看更多内容