I use machine learning to add color to black and white photos like this algorithm learns from a process of trial and error.

It looks at millions of images, and then it starts finding pageants step by step.

It learns how to color to black and white photos.

Eventually, you end up with something pretty accurate.

I tried to build a shortest algorithm, my code using tensorflow, Google's open source machine learning platform.

I'm interested in finding ways to make machine learning easy to grasp.

I open source a cone and now fished it to 200 people.

Use it per week, the easier you make a learning algorithm that more accessible becomes people can play around.

By then, who knows what that's gonna lead to?

The more we open source, the more we can learn from each other.