This is more or less a continuation of the last post where I described how to use a free Tesla K80 GPU in the cloud. I pointed out some problems I had which appeared during my time I did a project in …

There is one problem with machine learning. We don't all have a good GPU or none at all. As a student it is quite common to just have a laptop which normally doesn't really have a GPU and of course al…

This post is again about machine learning and not about optimization but I would like to mention some things beforehand. After my last blog article I started my master's degree in Scientifc Computing …

It's a long dream of mine to build something like a chess engine because I love to play chess. Well there are chess engines all over the place but it's something different when you build it by your ow…

This is the third blog entry about MNIST (the handwritten digit database). In the first one I explained how to digitize your own handwritten digits. If you missed it, check it out here. The second one…

In the last blog entry you learned how to digitize a single handwritten digit. The downsides were that you have to capture a single digit and the image should be quadratic. But that's not the case. No…

There are a lot of articles about MNIST and how to learn handwritten digits. So this one will be just another one? Nope, I'll use the newest available library Tensorflow by Google, but they have there…

It's time to use our machine learning knowledge in combination with real data. There is no need to teach logical functions or other well defined things to the computer. But do you know whether you wou…