More FF10 cover refinements.

Working on the cover for our next report "Learning with Limited Labelled Data". Planning to generate the illustration from a forked version of @_cjwallace's active learning demo notebook.

Back to work on the prototype. Got the transitions working: select points, label points, retrain model.

I'm working on putting my personal online presence in order. First up, a page for my résumé.

From: https://resume.grantcuster.com/

Using face-tracking and parallax to add depth to a website. Cool idea by Rupert Parry.

From: https://depth-index-demo.glitch.me/

John Caserta's website contains a link to print the website as a book.

From: http://johncaserta.com/

Trying to decide how to show the selected points. This is a little harsh.

This is great and it's going to take me a while to finish. It shows how a thoughtful interface and framing can change how a process feels (compare this to going through your following list in the normal Twitter interface).

From: https://tokimeki-unfollow.glitch.me

I got the MNIST images rendering in the active learning prototype. White here are the images selected for labeling for the next round.

Rasmus Andersson's favorite technical papers.

From: https://www.dropbox.com/sh/is0sy5350lr4v9j/AADQlhVSQcRw6vCNKQgGWelqa

Lots of neat generative sketches by Kjetil Golid.

From: https://generated.space/

First pass of active learning rounds on MNIST in the prototype. I need to think through what the transitions should be more, but this looks promising.

Oooo I bet there are some interesting things to be done with context.isPointinPath().

From: https://beta.observablehq.com/@mbostock/pixelated-world

Mushy: neural network generated isometric tiles by Everest Pipkin.

From: https://everestpipkin.itch.io/mushy

I'm making a notebook to visualize and figure out what frame and matting options I should choose.

I changed how I'm handling transparency thresholding so the blobs are a lot less muddy now.

From: https://grantcuster.github.io/umap-explorer/

I didn't think this all the way through and ran UMAP on each of these groups separately instead of at the same time.

Starting to mock up the prototype.

I added T-SNE and UMAP with min_dist=0.8 algorithm options to the UMAP explorer. Three.js & tween.js animating the transition of 70,000 points no problem.

From: https://grantcuster.github.io/umap-explorer

Working on getting T-SNE running in the MNIST explorer.