CFIS

It started with pybind11 envy.

Traditionally the most popular way to run Ruby on Windows is using DevKit, which installs a complete Msys/MingW64 environment.

After supporting linear regression and TensorBoard, the next step for the tensorflow-ruby gem is to run MNIST, the “Hello World” of deep learning.

This evening I gave a talk about tensorflow-ruby to Seattle.rb, the oldest Ruby group in the world.

Today was my first day at Pattern Computer.

Now that tensorflow-ruby supports linear regression, its time to implement support for TensorBoard which helps you visualize how your model is working.

Thanksgiving. 10am. 23 degrees.

The TensforFlow Ruby bindings have achieved a milestone – its now possible to train a model to solve linear regression.

Last Saturday, Yue and I went snorkeling with chum salmon on the Hood Canal.

Since I recently left Zerista, I’ve had time some time to take a step back and think about what type of problems I want to work on next.