So today we are going to do something really awesome. Operationalize Keras with Azure Machine Learning. Why in the world would we want to do this? Well we can configure Deep Neural Nets and train them on GPU. In fact, in this article, we will train a 2 depth neural network which outputs a linear prediction of energy efficiency of buildings and then operationalize that GPU trained network on Azure Machine Learning for production API usage.
So today I have decided to actually begin a write up on where I’m headed. Its taken a long while to come up with what my next adventure after food trucks was going to be, especially with all of the things you can do with embedded technologies and machine learning. So here it is, a self driving race car.
In this article I aim to lay out the high level plan of attack for what my team and I are building and some of the direction on where we are headed.
So I just completed an incredible project with Brain Thermal Tunnel Genix, where I learned so much about pattern recognition, machine learning and taking research and algorithms and pushing those into a production environment where it can be integrated into a real product. Today’s article takes those lessons and provides a sample on how to perform complex modelling and operationalize it in the cloud. The accompanying Gallery Example can be found here.
As Azure becomes more and more popular and I encounter more startups, I find myself doing this tutorial all the time and explaining it. Therefor, I have decided to write a blog article with pictures, to make my life (and yours) easier.
What is BizSpark
BizSpark is the best thing since sliced bread for a startup. It is literally every development tool and license that Microsoft has to offer for free for commercial purposes for 3 years. Not only that, but you get $150/month (as of this writing) in Azure for 3 years as well. As if it couldn’t get any better, you get access to reduced pricing on various products from Microsoft Partners. Microsoft being such a giant of a company, there are a TON of partners you get special pricing from. BizSpark also includes product licensing such as just your simple windows licenses, or visual studio licenses, and even SQL Server licenses. Its everything! Usually at this point I get the question, so what’s the catch? There is no catch! Microsoft wants you to use their tools and be successful with their tools so that when you become a giant company, you are using their tools and not a competitors. Therefor Microsoft gives these tools to high potential startups for free! If you think you qualify, apply or come to an event I attend (usually found on the events tab). You can also ping me on twitter @DavidCrook1988.
As many of you may know at this point, I am relocating to South Florida. Final location to be determined, but will probably be renting around Pompano Beach or Fort Lauderdale while working out of Venture Hive and the Microsoft Fort Lauderdale Offices. So what does this have to do with Zillow? Well, It has EVERYTHING to do with Zillow. What I’ve found while searching for homes is that between Realtors, Zillow and Trulia, they really just don’t have a predictive analytics solution that works for me. So I decided to give a shot at AzureML to mash together a few datasets to send me notifications more to my liking than is currently being sent. So step 1 in this plan is to data mine Zillow. Luckily, Zillow has an api for that. Or if you are feeling particularly frisky, Zillow gets their data from ArcGIS (example for Raleigh). So lets get cracking…