Encoding Structure in Boolean Space
Encoding Structure in Boolean Space
复制标题
布尔空间中的编码结构
DOI：
10.1007/978-1-4471-1599-1_57
复制
发表时间：
1998
期刊：
影响因子：
--
通讯作者：
P. Kanerva
中科院分区：
文献类型：
--
作者：
P. Kanerva
分布式表示的递归结构与变量绑定的探索，使用二进制向量和只有一个合成函数自然神经网络。该系统是仿照全息简化表示，但它的两个组成运营商的阈值总和。绑定通过对角色和填充符的向量进行AND运算来完成，绑定对通过OR运算进行组合或合并。实现AND和OR的阈值是不同的，但建议在某些条件下，单个阈值可能足够接近它们，以允许其用于绑定和合并。因此，使用变量绑定的递归结构构建可以通过适合神经网络的简单机制来实现。
Distributed representation of recursive structure with variable binding is explored, using binary vectors and only one composition function natural to neural nets. The system is modeled after Holographic Reduced Representation, but both of its composition operators are thresholded sums. Binding is done by ANDing the vectors for a role and a filler, and bound pairs are combined or merged by ORing. The thresholds for realizing AND and OR are different, but it is suggested that under certain conditions a singe threshold might approximate them closely enough to allow its use for both binding and merging. It therefore appears that recursive structure building that employs variable binding can be achieved with simple mechanisms suitable for neural nets.