Silva 和 Almeida 的反向传播算法中 u 和 d 的合适值是多少?
Silva 和 Almeida 的算法通过为每个权重引入单独的自适应学习率来改进现有的反向传播算法。新学习率的值计算如下:
我读到常量 u
和 d
设置为 u > 1 和 d < 1.
.这些限制相当广泛,因此是否有任何设置这些值的一般准则,或者我是否必须通过针对我的具体问题进行实验来找出答案?
Silva and Almeida's algorithm improves on the existing backpropagation algorithm by introducing individual, adaptive learning-rates for each weight. The value for the new learning rate is computed as follows:
I read that the constants u
and d
are set to be u > 1
and d < 1
. Those constraints are rather broad, so are there any general guidelines for setting these values or do I have to figure it out by experimentation for my specific problem?
如果你对这篇内容有疑问,欢迎到本站社区发帖提问 参与讨论,获取更多帮助,或者扫码二维码加入 Web 技术交流群。
绑定邮箱获取回复消息
由于您还没有绑定你的真实邮箱,如果其他用户或者作者回复了您的评论,将不能在第一时间通知您!
发布评论
评论(1)
我读过适合大多数问题的良好“起始”值是尝试 u = 1.2 和 d = 0.8 但我现在找不到来源。
编辑:我找到了,PDF第10-11页
另请注意关于如何通过引入动量项来改进算法的评论,如果您还没有的话......
I have read that good "starting" values to fit most problems are to try u = 1.2 and d = 0.8 but i can't find the source right now.
Edit: I found it, PDF page 10-11
Also note the comments about how to improve upon the algorithm by introducing a momentum term, if you don't have that already...