专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US5245696A Evolution and learning in neural networks: the number and distribution of learning trials affect the rate of evolution 失效
标题翻译：神经网络的进化和学习：学习试验的数量和分布影响进化速度
公开(公告)号：US5245696A
公开(公告)日：1993-09-14
申请号：US616029
申请日：1990-11-21
申请人： David G. Stork , Ronald C. Keesing
发明人： David G. Stork , Ronald C. Keesing
IPC分类号： G06F15/18 , G06G7/60 , G06N3/08 , G06N99/00
CPC分类号： G06K9/4628 , G06K9/6229 , G06N3/086
摘要： The present invention relates to the interrelationships between nature (as mediated by evolution and genetic algorithms) and nurture (as mediated by gradient-descent supervised learning) in a population of neural networks for pattern recognition. The Baldwin effect is demonstrated that learning can change the rate of evolution of the population's genome - a "pseudo-Lamarkian" process, in which information learned is ultimately encoded in the genome by a purely Darwinian process. Selectivity is shown for this effect: too much learning or too little learning in each generation leads to slow evolution of the genome, whereas an intermediate amount leads to most rapid evolution. For a given number of learning trials throughout a population, the most rapid evolution occurs if different individuals each receive a different number of learning trials, rather than the same number. Because all biological networks possess structure due to evolution, it is important that such interactions between learning and evolution be understood. Hybrid systems can take advantage both of gradient descents (learning) and large jumps (genetic algorithms) in very complicated energy landscapes and hence may play an increasingly important role in the design of artificial neural systems.
摘要翻译：本发明涉及在模式识别的神经网络群体中的自然（由进化和遗传算法介导）和培养（由梯度下降监督学习介导）之间的相互关系。 Baldwin效应被证明，学习可以改变人群基因组的进化速度 - 一个“伪拉马契”过程，其中所学的信息最终通过纯达尔文过程在基因组中编码。显示出这种效果的选择性：每一代学习过多或学习太少导致基因组进化缓慢，而中等数量则导致最快速的进化。对于整个人口中的一定数量的学习试验，如果不同的人每次接受不同数量的学习试验而不是相同的数字，则发生最快速的进化。由于所有生物网络由于进化而具有结构，所以要了解学习与进化之间的这种相互作用是很重要的。混合系统可以在非常复杂的能量景观中利用梯度下降（学习）和大跳跃（遗传算法），因此可能在人造神经系统的设计中发挥越来越重要的作用。

IPRDB

热门服务

关于我们

友情链接

联系方式