arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1306.6041cs.NEcond-mat.dis-nnnlin.AOnlin.CDphysics.bio-ph
收藏

随机自动机网络中的学习、泛化和函数熵

Learning, Generalization, and Functional Entropy in Random Automata Networks

Alireza Goudarzi, Christof Teuscher, Natali Gulbahce, Thimo Rohlf

摘要:

\citep{broeck90:physicalreview,patarnello87:europhys}已经表明,前馈布尔网络可以学习执行特定的简单任务,并且如果只提供学习示例的子集用于学习,则可以很好地泛化。在这里,我们扩展了这方面的工作,并通过实验表明,随机布尔网络(RBN),其中的互连和布尔传递函数最初是随机选择的,可以通过使用状态拓扑进化来解决简单的任务。我们测量的学习和泛化性能,调查的影响,平均节点连接$K$,系统大小$N$,并引入一个新的措施,可以更好地描述网络的学习和泛化行为。我们表明,最大熵网络的连通性的规模作为系统大小的幂律$N$。我们的研究结果表明,具有较高平均连通性的网络$K$(超临界)实现更高的记忆和部分泛化。然而,在临界连通性附近,网络在奇偶任务上表现出更高的完美泛化能力。

英文摘要:

It has been shown \citep{broeck90:physicalreview,patarnello87:europhys} that feedforward Boolean networks can learn to perform specific simple tasks and generalize well if only a subset of the learning examples is provided for learning. Here, we extend this body of work and show experimentally that random Boolean networks (RBNs), where both the interconnections and the Boolean transfer functions are chosen at random initially, can be evolved by using a state-topology evolution to solve simple tasks. We measure the learning and generalization performance, investigate the influence of the average node connectivity $K$, the system size $N$, and introduce a new measure that allows to better describe the network's learning and generalization behavior. We show that the connectivity of the maximum entropy networks scales as a power-law of the system size $N$. Our results show that networks with higher average connectivity $K$ (supercritical) achieve higher memorization and partial generalization. However, near critical connectivity, the networks show a higher perfect generalization on the even-odd task.

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。

↑