Task Decomposition and Correlations in Growing Artificial Neural Networks
暂无分享，去创建一个
To reduce the engineering efforts for the design of neural network architectures a data driven algorithm is desirable which constructs a network during the learning process. For structure adaptation different approaches with evolutionary algorithms (Voigt et. al., 1993), growth algorithms (Fahlmann et. al., 1990), and others are used.
[1] E I. Smieja,et al. Reflective Modular Neural Network Systems , 1992 .
[2] Sukhan Lee,et al. A Gaussian potential function network with hierarchically self-organizing learning , 1991, Neural Networks.
[3] Christian Lebiere,et al. The Cascade-Correlation Learning Architecture , 1989, NIPS.
[4] Helge J. Ritter,et al. Generalization Abilities of Cascade Network Architecture , 1992, NIPS.
[5] Michael I. Jordan,et al. Hierarchies of Adaptive Experts , 1991, NIPS.