I really like the conversations you have with your dad. They are quite interesting. It's usually the other way around for me, although I do know a good deal of the sciences, and he would end his little "lecture" by going off on a tangent.
Thank you! My dad is a cool guy. He’s always supported me in my interests - only a father’s love could withstand taking your daughter to the same exhibits in the same museum multiple times a year since she was born. But he seems to enjoy the sciences as well, and he’s a smart guy.
And ooooh do I know about “lectures.” My mom is like that sometimes. I think I get it from her. Not that it’s a bad thing! I find it’s very easy to go off on tangents when dealing with science especially, because everything relates to each other in some way. Once I was in a debate group about the hydrogen bomb and I ended up talking about the invention of Silly Putty.
Google’s X Lab designed a particular neural network to discern whether an algorithm could learn to recognize faces without being fed information on exactly what a face was. It did great at that task.
It also found cat videos quite well:
The “brain” simulation was exposed to 10 million randomly selected YouTube video thumbnails over the course of three days and, after being presented with a list of 20,000 different items, it began to recognize pictures of cats using a “deep learning” algorithm. This was despite being fed no information on distinguishing features that might help identify one.
On the surface, it’s a joke about the impending cat video singularity. But it’s a pretty awesome example of machine learning, too. It means that with careful programming, a synthetic network can learn fairly advanced patterns in completely novel data, like cat faces, or what a cat even IS.