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

Changing colors to rainbow colors #104

Open
wants to merge 86 commits into
base: xor
Choose a base branch
from

Conversation

jonathan-richer
Copy link
Contributor

Rainbow!

I changed the colorMode to HSB and the fill arguents
to work with, so it looks more like:

In setup:

colorMode(HSB);

And draw:

for (let i = 0; i < cols; i++) {
    for (let j = 0; j < rows; j++) {
      let x1 = i / cols;
      let x2 = j / rows;
      let inputs = [x1, x2];
      let y = nn.predict(inputs);
      noStroke();
      fill(y * 360, 100, 100);
      rect(i * resolution, j * resolution, resolution, resolution);
}

Maik1999 and others added 30 commits February 5, 2018 15:26
Coding Challenge: handwritten number recognition
This is much more appealing !!!! Keep up the good work.
Adding to README the CircleCi Build Status.
Moved the To-Do list in the README
…t when the dimensions of the matrices don't match. Also added tests for them.
Added error handling for elementwise functions
Alter how mnist files are loaded
shiffman and others added 28 commits February 11, 2018 09:50
User Input needs to be normalized
Updated p5.js to v0.6.0, removed unused sound lib and deleted local libs
…lass

Manage activation function as a class
Added links to the mentioned pull requests in README
Dear Diary,

I spent the day recording a set of video tutorials about how to do image classification with a simple "toy" neural network. There are lots of problems with this and the goal is purely educational and to have some fun. I hope to improve this example in the future. It could use an intrface and some animations, the softmax function, and working with a larger dataset and ml5/deeplearn.js.

yours forever,
The Coding Train (choo choo)
nothing to see here yet!
This here is the start of code I need for my neuro-evolution examples.
So far I have only implemented "copy()" and "mutate()" ok! I still need
to do "crossover()" and implement the GA itself of course. For
reference the live stream is here:

https://www.youtube.com/watch?v=ASnCXW6pPSY
This adds a test for the `Matrix.copy()` function.
Create a README in the xor example
Copy link
Collaborator

@Versatilus Versatilus left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'm guessing you might've accidentally done a pull request to the wrong branch of the repository. I can fix it to point to master if you can't find the right option. I think you can fix it if you edit your initial post or post title.

We can probably add this with those changes, but I think it would be even cooler to add your other example in its own folder instead of changing this one.

@@ -1,7 +1,6 @@
let nn;
let lr_slider;

let training_data = [{
et training_data = [{
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It looks like you accidentally deleted the 'l' off of "let" right here.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

probably, I will fix this... thank you!

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.