Welcome to the second week
of this course. You learned about how to compute statistical analysis
of a time series. In this week, you'll
learn to apply a new network to these sequences. Yeah, we'll start with
a relatively simple DNN, and if you remember
DNNs all the way back like at the beginning
of the specialization, so you're going to be able
to bring those skills to bear on time-series data. So we're going to build
a very simple DNN just like a three-layer DNN. Then one technique
though that's I find really useful that you're
going to learn this week, is being able to tune the
learning rate of the optimizer. We'll all spent a lot of time
hand-tuning learning rate. One of my most distinctive
memories from couple of decades ago was
a summer intern at Microsoft research
staying up until 3:00 AM in the office,
hand-tuning learning rates. I wish I could tune
my own learning rate sometimes. So I think giving people
a systematic way to do this, will be very useful. Yeah. I think so, and I know I've spent
too many sleepless nights at it. So we tried to automate
it here and so teach you a technique for automating it and hopefully it'll be useful, and hopefully it'll help
you to start learning how to predict
your time series data. By the end of this week, you
have trained DNN on time series data that
you saw last week and you get to see
how well it does. Please go onto to the next video.