Yao X, Liu Y
Sch. of Comput. Sci., New South Wales Univ., Canberra, ACT.
IEEE Trans Neural Netw. 1997;8(3):694-713. doi: 10.1109/72.572107.
This paper presents a new evolutionary system, i.e., EPNet, for evolving artificial neural networks (ANNs). The evolutionary algorithm used in EPNet is based on Fogel's evolutionary programming (EP). Unlike most previous studies on evolving ANN's, this paper puts its emphasis on evolving ANN's behaviors. Five mutation operators proposed in EPNet reflect such an emphasis on evolving behaviors. Close behavioral links between parents and their offspring are maintained by various mutations, such as partial training and node splitting. EPNet evolves ANN's architectures and connection weights (including biases) simultaneously in order to reduce the noise in fitness evaluation. The parsimony of evolved ANN's is encouraged by preferring node/connection deletion to addition. EPNet has been tested on a number of benchmark problems in machine learning and ANNs, such as the parity problem, the medical diagnosis problems, the Australian credit card assessment problem, and the Mackey-Glass time series prediction problem. The experimental results show that EPNet can produce very compact ANNs with good generalization ability in comparison with other algorithms.
本文提出了一种用于演化人工神经网络（ANN）的新演化系统，即EPNet。EPNet中使用的演化算法基于福格尔的演化规划（EP）。与之前大多数关于演化ANN的研究不同，本文着重于演化ANN的行为。EPNet中提出的五个变异算子体现了这种对行为演化的重视。通过各种变异，如部分训练和节点分裂，保持了父代与子代之间紧密的行为联系。EPNet同时演化ANN的架构和连接权重（包括偏置），以减少适应度评估中的噪声。通过优先删除节点/连接而非添加，鼓励演化后的ANN保持简洁。EPNet已在机器学习和ANN的一些基准问题上进行了测试，如奇偶问题、医学诊断问题、澳大利亚信用卡评估问题以及Mackey-Glass时间序列预测问题。实验结果表明，与其他算法相比，EPNet能够生成非常紧凑且具有良好泛化能力的ANN。
