We will cover the following tasks in 31 minutes:
In this chapter we will discuss Neural Networks, I’ll give you a quick history of where we are on machine learning in 2018, I’ll introduce you to the Rhyme Interface, and at the end I’ll share a bit about myself.
In this section I will start by showing you a visual representation of a tensor. We will then move onto creating 60,000 tensors in the same form of the illustrated one I showed prior. We will do this by using the array_reshape function in Keras.
One Hot Encoding
This is a life saver. We need to make sure the Output is in the same form as the Input. So we use “One Hot Encoding”. Come in and you’ll see how this is done.
Building Out Model
So now it’s time to start constructing our model. We will build an Input Layer with two Hidden Layers. Easy squeezy.
Loss Optimizer and Model Run
We need to build a loss optimizer so we can spot when the model starts over fitting. We will do that and then we will train the model on the Training Images and Labels.
Test Data and Summary
The model did well! But how about on numbers it hasn’t seen (true test), which could really be mine or yours. In this case its High School Students. After we’re done with that I will recap and we can get on with our next tutorial.
About the Host (Chris Shockley)
I am a R enthusiast, hiker, and amateur astronomer. My favorite hike is located in Mt. Rainier National Park, my favorite Deep Sky Object is Alberio, and my favorite R package is dplyr (since I use it everyday). I am single too. Maybe because I spend too much time playing? I have a dog named Coog (Lllasa Apso), who would rather be outside than inside, which means I have to take him on a lot of walks. I work as a Data Analyst/Financial Analyst for a Metals Co. located in Seattle, WA. I have been in my current position for 4 years. My hope is that I can help you, even if its with my enthusiasm. Yes you can learn R and the Rhyme Interface will help you. But. You also must take what you learn and practice, practice, practice. So... Let's get after it. See you soon.