Jimmie's Mostly Tech Blog

Jimmie Butler

Jimmie Butler

2 followers

Developer with around 10 years experience. Full stack developer, with experience in dev-ops, and interest in machine learning.

Available for work.

ML Experiment Log: Squaring as activation layer

Oct 8, 20224 min read

The purpose of an activation layer is to add some non-linearity to the network. This allows expressing much more complex tasks with our networks. But...

ML Experiment Log: Squaring as activation layer

On the fly expansion of linear layers

Sep 27, 20223 min read

Two brains are better than one. ยท A linear layer takes a set of inputs, and for each node in its layer it sums weights*inputs to calculate the node...

On the fly expansion of linear layers

ML Experiment Log - Polynomial Network + MNIST

Sep 8, 20222 min read

I wanted to try implementing previous work nn + polynomial solvers against a larger problem, in this case MNIST. For anyone hopping in here, I'm...

ML Experiment Log - Polynomial Network + MNIST

ML Experiment Log - NN + Polynomial Solvers Pt. 2

Sep 5, 20222 min read

In the previous attempt, a polynomial based neural network was setup and we had some inconsistent results coming back. My assumption at that point was...

ML Experiment Log - NN + Polynomial Solvers Pt. 2

ML Experiment Log - NN + Polynomial Solvers

Sep 3, 20223 min read

This approach doesn't seem to produce good results. The idea is to create a neural network completely from polynomials (doesn't really require much),...

ML Experiment Log - NN + Polynomial Solvers

ML Experiment Log - Differentiable graph environment

Sep 3, 20222 min read

I'm interested in generative design, especially geometric deep learning. For a simple environment I'd like to have an environment where given some...

ML Experiment Log - Differentiable graph environment