Discrete weights with neural network toolbox

2 次查看（过去 30 天）
circuit_designer5172
评论： Jules BROCHARD 2018-1-25
Hello, I am building a custom neural network. In the application I am attempting to model it is only possible to have weights of discrete values [-2, -1, 0, 1, 2]. I want to use this network to perform the training using the built-in functions, but don't want to get weights back that are 1.24345932 and have to round it and sacrifice accuracy in the testing phase. I have found some documentation that you can use the command net.inputs{1}.exampleInput = [...] but it doesn't realize that I want the values to be discrete and it resets the size of the inputs. Thank you!

请先登录，再回答此问题。

采纳的回答

Eric Lin
Eric Lin 2015-6-19
Constraining network weights is not possible with the built-in Neural Network Toolbox functions as the training algorithms are all gradient-based. If you would like to implement your own training algorithm, consider using the intlinprog or ga functions which perform mixed-integer optimization.
  2 个评论
Alexandra Tzilivaki
Alexandra Tzilivaki 2017-11-6
Hello Eric. Is it possible however to have non negative weights? If so, which is the best train function for non negative weights?
Many thanks in advance
Jules BROCHARD
Jules BROCHARD 2018-1-25
If you build you own transfer function, you use a transformation, such as the exponential*, to map R into R+ before inputing them in your usual transfering function. In practice your weight will still be negative but they will be used as positive number.
*: beware of the distortion of space it induces. Oh and don't forget to adjust the gradient derivative accordingly :)

请先登录，再进行评论。

更多回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Sequence and Numeric Feature Data Workflows 的更多信息

标签

产品

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by