Learning by gradient descent in function space
Learning by gradient descent in function space
复制标题
通过函数空间中的梯度下降进行学习
DOI：
10.1109/icsmc.1990.142101
复制
发表时间：
1990
期刊：
影响因子：
--
通讯作者：
G. Mani
中科院分区：
文献类型：
--
作者：
G. Mani
演示了连接主义网络的使用，其中每个节点执行不同的功能以实现高效的监督学习。提出了一种改进的反向传播算法，该算法在函数空间中执行梯度下降，并讨论了其优点。建议的范例的好处包括更快的学习和易于解释的训练网络。这种方法与其他相关的方法，包括传统的反向传播或重新加权相结合的潜力进行了探讨。<<ETX>>
The use of connectionist networks in which each node executes a different function to achieve efficient supervised learning is demonstrated. A modified backpropagation algorithm for such networks, which performs gradient descent in function space, is presented, and its advantages are discussed. The benefits of the suggested paradigm include faster learning and ease of interpretation of the trained network. The potential for combining this approach with other related approaches, including traditional backpropagation or reweighting is explored.<<ETX>>