Motherboard has the article A New Object-Recognition Algorithm Could Change the Face of Machine Learning.

The report, which comes courtesy of researchers at NYU and MIT, introduces the Bayesian program learning (BPL) framework, a new machine learning model capable of mimicking the human mind’s capacity for generalizing from single examples. It’s a model that “learns to learn.”

I am always interested in possible breakthroughs that might lead to being able to do things that we didn’t think were possible before. I have heard of Bayesian probability before, but since I have always had troubles understanding some aspects of probability, it does not surprise me that I am having trouble coming to terms with Bayesian probability. My learning experience tells me that the more times I read about a topic, the more I come to understand it. That is why I find it useful to read things that I do not understand.