Let’s look at how to explore images in Python. We’ll use the popular and active Pillow fork of PIL, the Python Imaging Library.

Is there sarcasm on the Internet? OK, that’s an easy one. Here’s a more difficult question: can an AI be trained to detect that sarcasm? The first step to training that algorithm would be to create a corpus of sarcastic statements from the Internet. Fortunately, there’s a lot of sarcasm out there and, even more fortunately, much of it is already labeled.

What goes on inside the black box of a machine learning algorithm? While it may be impossible for a human to understand precisely why a large neural network produced the results it did, some algorithms are far more transparent. Decision trees are just such an example of a machine learning algorithm whose results can be understood by people.

The following is my handy post for vim notes, tips, and tricks.

The story of rabbits in Australia, and the resulting eradication efforts, provides a cautionary tale about viruses and immunity. This post will explore the growth of that population and the government’s response to it.

Can AI create art? We’re still far away from knowing what (if any) the limits of AI in the art world are, but a recent paper takes a sizeable step in that direction. The paper, A neural Algorithm of Artistic Style describes using deep neural networks to combine the content of one image with the style of another. This opens up incredible possibilities. An AI could be taught how to paint in the style of Picasso, but use your portrait of the subject. And, even cooler, another researcher developed an implementation using Torch and posted it on Github.

How can I convert my Jupyter Notebooks to Jekyll-ready blog posts in a single click? How do I streamline that process so that I can quickly fix typos, better explain topics, or add new ideas without the hassle of manually converting the notebooks to something more Jekyll-friendly? To answer this, I wrote a simple batch script that allows me to edit posts in Jupyter Notebooks and then post them as HTMLs. This is built for Windows and using Github Pages, which is what I use to host this blog.