Kwok T Y, Yeung D Y
Dept. of Comput. Sci., Hong Kong Univ. of Sci. and Technol., Kowloon.
IEEE Trans Neural Netw. 1997;8(3):630-45. doi: 10.1109/72.572102.
In this survey paper, we review the constructive algorithms for structure learning in feedforward neural networks for regression problems. The basic idea is to start with a small network, then add hidden units and weights incrementally until a satisfactory solution is found. By formulating the whole problem as a state-space search, we first describe the general issues in constructive algorithms, with special emphasis on the search strategy. A taxonomy, based on the differences in the state transition mapping, the training algorithm, and the network architecture, is then presented.
在这篇综述论文中，我们回顾了用于回归问题的前馈神经网络结构学习的构造算法。基本思想是从一个小网络开始，然后逐步添加隐藏单元和权重，直到找到一个满意的解决方案。通过将整个问题表述为状态空间搜索，我们首先描述构造算法中的一般问题，特别强调搜索策略。然后，基于状态转移映射、训练算法和网络架构的差异，给出了一种分类法。
