Staley M
Department of Physics, University of Guelph, Ontario, Canada.
Int J Neural Syst. 1995 Mar;6(1):43-59. doi: 10.1142/s0129065795000056.
A new feedforward architecture is presented for empirical model building and regression. The network consists of two hidden layers of units, where each unit utilizes a piece-wise linear activation function. A procedure for determining both the number of units and their connectivity is developed. The most notable feature of the network is its associated learning algorithm which allows for recursive updating of the parameters. A smoothness constraint is employed to limit the range of solutions, so that practical models may be built with small amounts of data. The network is applied to some function estimation tasks, as well as to a forecasting problem using data from the Santa Fe Institute time-series competition.
提出了一种用于经验模型构建和回归的新前馈架构。该网络由两个隐藏单元层组成，其中每个单元使用分段线性激活函数。开发了一种确定单元数量及其连接性的方法。该网络最显著的特征是其相关的学习算法，该算法允许对参数进行递归更新。采用平滑约束来限制解的范围，以便可以用少量数据构建实际模型。该网络应用于一些函数估计任务，以及使用圣塔菲研究所时间序列竞赛的数据进行预测的问题。
