Train linear combinations of inputs #88
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
The program example/train_and_write.f90 now demonstrates how to train a simple neural network starting from a randomized initial condition and how to write the initial network and the trained network to separate JSON files, where the network has - 2 hidden layers, - 2 nodes per layer for the input, hidden, and output layers, and - desired outputs identically matching the corresponding inputs. With ReLU activation functions, the desired network therefore contains weights corresponding to identity matrices and biases that vanish everywhere. The initial condition is the desired network with all weights and biases perturbed by a random variable that is uniformly distributed on the interval [0,0.1].
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This pull request adds
example/fit-polynomials.f90, which trains a neural network to learn linear combinations of the inputs. The neural network learns to map eight inputs,x(1:8), to six outputs corresponding toy(x) = [x(1), x(2) + x(3), x(4), x(5), 0.5*x(6) + 1.5*x(7), x(8)], where the network usesy(x) = [x(2), x(3), x(4), x(5), x(6), x(7), and