Electrical Engineering Department, NWFP UET Peshawar, Pakistan.
Evol Comput. 2011 Fall;19(3):469-523. doi: 10.1162/EVCO_a_00043. Epub 2011 Jun 20.
Although artificial neural networks have taken their inspiration from natural neurological systems, they have largely ignored the genetic basis of neural functions. Indeed, evolutionary approaches have mainly assumed that neural learning is associated with the adjustment of synaptic weights. The goal of this paper is to use evolutionary approaches to find suitable computational functions that are analogous to natural sub-components of biological neurons and demonstrate that intelligent behavior can be produced as a result of this additional biological plausibility. Our model allows neurons, dendrites, and axon branches to grow or die so that synaptic morphology can change and affect information processing while solving a computational problem. The compartmental model of a neuron consists of a collection of seven chromosomes encoding distinct computational functions inside the neuron. Since the equivalent computational functions of neural components are very complex and in some cases unknown, we have used a form of genetic programming known as Cartesian genetic programming (CGP) to obtain these functions. We start with a small random network of soma, dendrites, and neurites that develops during problem solving by repeatedly executing the seven chromosomal programs that have been found by evolution. We have evaluated the learning potential of this system in the context of a well-known single agent learning problem, known as Wumpus World. We also examined the harder problem of learning in a competitive environment for two antagonistic agents, in which both agents are controlled by independent CGP computational networks (CGPCN). Our results show that the agents exhibit interesting learning capabilities.
虽然人工神经网络受到自然神经系统的启发，但它们在很大程度上忽略了神经功能的遗传基础。事实上，进化方法主要假设神经学习与突触权重的调整有关。本文的目的是利用进化方法找到与生物神经元的自然子组件类似的合适计算功能，并证明智能行为可以由此产生额外的生物学合理性。我们的模型允许神经元、树突和轴突分支生长或死亡，从而改变突触形态，并在解决计算问题的同时影响信息处理。神经元的分区模型由一组七个染色体组成，这些染色体编码神经元内部的不同计算功能。由于神经成分的等效计算功能非常复杂，在某些情况下是未知的，我们使用了一种称为笛卡尔遗传编程（CGP）的遗传编程形式来获得这些功能。我们从一个由 soma、树突和轴突组成的小随机网络开始，通过反复执行进化找到的七个染色体程序来解决问题。我们在一个名为 Wumpus World 的著名单代理学习问题的背景下评估了这个系统的学习潜力。我们还研究了在两个对抗性代理的竞争环境中学习的更困难的问题，其中两个代理都由独立的 CGP 计算网络（CGPCN）控制。我们的结果表明，代理表现出有趣的学习能力。
