arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1408.1784cond-mat.dis-nncond-mat.stat-mechcs.LGq-bio.NC
收藏

二元突触学习计算困难的起源

Origin of the computational hardness for learning with binary synapses

Tokyo Institute of Technology(东京工业大学)

Haiping Huang, Yoshiyuki Kabashima

摘要:

二进制感知器中的监督学习能够通过适当分配二进制突触权重来对大量随机模式进行分类。然而,要在实践中找到这样的任务,是一个相当不平凡的任务。权空间结构和算法难度之间的关系尚未完全理解。为此,我们从权的平衡解出发,通过探索权空间的结构,解析地导出了二元预振子问题的Franz-Parisi势,揭示了权空间\textemdash的几何组织,权空间是由孤立解组成的,而不是由指数级多个邻近解组成的簇.在权重空间中彼此远离的点状集群解释了先前观察到的随机局部搜索算法的玻璃状行为。

英文摘要:

Supervised learning in a binary perceptron is able to classify an extensive number of random patterns by a proper assignment of binary synaptic weights. However, to find such assignments in practice, is quite a nontrivial task. The relation between the weight space structure and the algorithmic hardness has not yet been fully understood. To this end, we analytically derive the Franz-Parisi potential for the binary preceptron problem, by starting from an equilibrium solution of weights and exploring the weight space structure around it. Our result reveals the geometrical organization of the weight space\textemdash the weight space is composed of isolated solutions, rather than clusters of exponentially many close-by solutions. The point-like clusters far apart from each other in the weight space explain the previously observed glassy behavior of stochastic local search heuristics.

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。

↑