arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1406.3185q-bio.NCcond-mat.dis-nncs.AI
收藏

尺度不变粗粒度存储器的通用构造

Generic construction of scale-invariantly coarse grained memory

Boston University(波士顿大学)

Karthik H. Shankar

摘要:

将最近的时间信息编码为空间分布的激活是必不可少的,以便同时访问整个最近的过去。任何依赖于过去来预测/计划未来的生物或合成代理都将被赋予这种空间分布的时间记忆。简单地说,我们预计资源限制将要求记忆系统只存储最有用的信息,以供未来预测。对于真实世界中的自然信号,表现出无尺度的时间波动,如果过去的信息是尺度不变的粗粒度的,则在存储器中编码的预测信息是最大的。在这里,我们研究的一般机制,构建一个规模不变的粗粒度存储系统。值得注意的是,一般的结构是相当于编码的线性组合的拉普拉斯变换的过去的信息和他们的近似逆。这揭示了记忆网络的一个基本结构约束,即试图最大限度地存储与自然世界相关的预测信息。

英文摘要:

Encoding temporal information from the recent past as spatially distributed activations is essential in order for the entire recent past to be simultaneously accessible. Any biological or synthetic agent that relies on the past to predict/plan the future, would be endowed with such a spatially distributed temporal memory. Simplistically, we would expect that resource limitations would demand the memory system to store only the most useful information for future prediction. For natural signals in real world which show scale free temporal fluctuations, the predictive information encoded in memory is maximal if the past information is scale invariantly coarse grained. Here we examine the general mechanism to construct a scale invariantly coarse grained memory system. Remarkably, the generic construction is equivalent to encoding the linear combinations of Laplace transform of the past information and their approximated inverses. This reveals a fundamental construction constraint on memory networks that attempt to maximize predictive information storage relevant to the natural world.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑