I often have a hard time understanding the terminology in machine learning, even after almost three years in the field. For example, what is a Deep Belief Network? I attended a whole summer school on Deep Learning, but I'm still not quite sure. I decided to take a leap of faith and assume this is not just because the Deep Belief Networks in my brain are not functioning properly (although I am sure this is a factor). So, I created a Machine Learning Glossary to try to define some of these terms. The glossary can be found here. I have tried to write in an unpretentious style, defining things systematically and leaving no "exercises to the reader". I also have a form for readers to request new definitions.
Because I did not bother learning how to render equations on my web site, I have had to write without equations. While annoying at times, I think this may actually help with the clarity of the definitions because I cannot hide behind equations and pretend that they explain everything. The lack of equations also keeps things at a high-level picture, which is the goal of the glossary.
At the moment the glossary is not a Wiki, but perhaps I will move to that model in the future. For now, it is an experiment and I hope it is helpful to at least a few people. If you have any thoughts on how I could improve the glossary, I would be interested to hear them!