Skip to content
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
wants to merge 13 commits into
base: master
Choose a base branch
from

Conversation

nicklandon2
Copy link

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.

nicklandon2 added 13 commits May 2, 2021 13:05
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
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant