联结理论的精炼:网络拓扑空间的遗传搜索
Connectionist Theory Refinement: Genetically Searching the Space of Network Topologies
摘要:
从一组示例中学习的算法理想地应该能够利用(a)丰富的计算能力和(b)特定领域知识的可用资源来提高其泛化能力。连接主义理论细化系统,使用背景知识来选择神经网络的拓扑结构和初始权重,已被证明是有效的利用特定领域的知识,但是,大多数不利用可用的计算能力。之所以会出现这种弱点,是因为它们缺乏改进所生成的神经网络拓扑结构的能力,从而限制了泛化,特别是在给定贫乏的领域理论时。我们提出了REGENT算法,它使用(a)特定领域的知识,以帮助创建一个初始人口的知识为基础的神经网络和(b)遗传算子的交叉和变异(专为知识为基础的网络),以不断寻找更好的网络拓扑结构。三个现实世界的域上的实验表明,我们的新算法是能够显着增加泛化相比,一个标准的连接主义理论的细化系统,以及我们以前的算法不断增长的知识为基础的网络。
英文摘要:
An algorithm that learns from a set of examples should ideally be able to exploit the available resources of (a) abundant computing power and (b) domain-specific knowledge to improve its ability to generalize. Connectionist theory-refinement systems, which use background knowledge to select a neural network's topology and initial weights, have proven to be effective at exploiting domain-specific knowledge; however, most do not exploit available computing power. This weakness occurs because they lack the ability to refine the topology of the neural networks they produce, thereby limiting generalization, especially when given impoverished domain theories. We present the REGENT algorithm which uses (a) domain-specific knowledge to help create an initial population of knowledge-based neural networks and (b) genetic operators of crossover and mutation (specifically designed for knowledge-based networks) to continually search for better network topologies. Experiments on three real-world domains indicate that our new algorithm is able to significantly increase generalization compared to a standard connectionist theory-refinement system, as well as our previous algorithm for growing knowledge-based networks.
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。