Discrete weights with neural network toolbox
3 views (last 30 days)
Show older comments
circuit_designer5172
on 18 Jun 2015
Commented: Jules BROCHARD
on 25 Jan 2018
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!
0 Comments
Accepted Answer
Eric Lin
on 19 Jun 2015
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 Comments
Alexandra Tzilivaki
on 6 Nov 2017
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
on 25 Jan 2018
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 :)
More Answers (0)
See Also
Categories
Find more on Sequence and Numeric Feature Data Workflows in Help Center and File Exchange
Products
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!