Post-it Notes

Collection of some quick ideas that I may or may not work on later.

1. Neural networks that take elements of a finite group as input

If we simply treat the input as general one-hot vectors the group structure will be lost. Could we somehow let the neural network be aware of the structure?

E.g. if the group is of order n then let the value of a neuron be a distribution on the n elements, and define a special type of neuron that takes two distributions P and Q and outputs R that is the distribution of c=ab^-1 where a~P and b~Q. We should be able to do this with some tensor arithmetic.

2. Iterative drawing for generating high-resolution images

What if instead of iteratively upsampling, we draw on a large canvas with progressively finer strokes?

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s