-
Notifications
You must be signed in to change notification settings - Fork 47
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Nick Landon CS 574 Final Project #13
Open
nicklandon2
wants to merge
13
commits into
forrestbao:master
Choose a base branch
from
nicklandon2:master
base: master
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
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
Added default miniNN file for reference
This file will address part 1 of project idea 2
This is the file where I will implement part 4 or project idea 2
Got rid of the explicit declaration of transfer matrices in the main method. Additionally, set up the main method to call a new method to create the new transfer matrices based on the supplied hidden layer sizes.
Added a function named createWs(), which will take the input, expected output, and the dimensions of the hidden layers and output a list of transfer matrices. Currently only giving the first matrix.
Finished the function createWs by adding a for loop to create the rest of the transfer matrices.
Fixed syntax issue
made the shell of the for loops and conditions to be checked while training to accommodate for the batch size and sample set larger than 1.
Copied the update weight method, but instead of updating the transfer matrices, this function just returns what the gradient would be if we were to update the transfer matrices.
Finished implementing the training method in order to operate base on sample set size and batch size, taking the averages of gradients before using the average matrices to update the transfer matrices.
Added the batchSize variable that is being used in the new training method to the initializing method and main method.
Added the printed text that will be displayed from the training method if verbose is set to true
added import calls for 'math' and 'random'
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.
I added a folder named 'FinalProjectCode' which contains three files for my final project. The file DefaultMiniNN.md is the exact same as the supplied MiniNN and was just used for reference. The file HiddenMiniNN.md is the code for part 1 of the MiniNN project, and the file BatchMiniNN.md is the code for part 4 of the MiniNN project.