Google #IO17 | Keynote | AutoML

Google #IO17 | Keynote | AutoML


designing better machine learning models but today it is really time-consuming it’s a painstaking effort of a few engineers and scientists mainly machine learning PhDs we wanted to be possible for hundreds of thousands of developers to use machine learning so what better way to do this than getting neural nets to design better neural nets we call this approach auto mo learning to learn so the way it works is we take a set of candidate neural nets think of these as little baby neural nets and we actually use a neural egg to iterate through them till we arrive at the best neural net we use a reinforcement learning approach and it’s the results are promising to do this is computationally hard but cloud tipi use put it in the realm of possibility we are already approaching state-of-the-art in standard tasks like C for image recognition so whenever I spend time with the team and think about neural nets building their own neural nets it reminds me of one of my favorite movies Inception and I tell them we must go deeper

3 comments

Leave a Reply

Your email address will not be published. Required fields are marked *