AI Everywhere: How Microsoft is Democratizing AI - Lightning Version

Editor's Notes

1. Deck can be found online at: http://www.slideshare.net/PaulPrae/ai-everywhere-how-microsoft-is-democratizing-ai Today, I’m going to walkthrough Microsoft’s approach to AI and how it will impact us as organizations, developers, and consumers.
2. I love AI. Like many tech companies right now, I’m going all in on artificial intelligence and machine learning. I’m currently taking courses at Georgia Tech in pursuit of the OMSCS. My AI studies began about 8 years ago at UGA. I’ve worked in the Microsoft ecosystem for about five years. My first time working with Microsoft tech seriously was when I worked at Microsoft as a SharePoint Support Engineer.
3. I recently attended Microsoft Ignite and the Data Science and Machine Learning Summit. And Satya certainly did answer, “What’s next in tech?”
4. What’s next in tech? Well according to Satya Nadella: Artificial Intelligence. Satya Nadella, the CEO of Microsoft, framed his entire Innovation Keynote around AI. And Microsoft is not alone. I’ve been keeping up with this stuff for awhile and the tech industry is blowing up. Image: http://news.microsoft.com/features/democratizing-ai/#sm.00000m3p4fmfl1e0bznn1xl9z26it#fpmWezjp3vR836Hq.97
5. This is what his entire keynote was framed around: Democratizing AI. Putting AI in the hands of everyone, everywhere. Reminiscent of Microsoft’s original vision. “We talked about a computer on every desk and in every home.” – Bill Gates http://www.telegraph.co.uk/technology/3357701/Bill-Gatess-dream-A-computer-in-every-home.html
6. https://en.wikipedia.org/wiki/Artificial_intelligence In the context of what Microsoft is up to, its really just smarter software. Examples: + Search is AI. The search engine is a rational agent. It’s goal is to find you the most relevant results. It perceives your query, tries to understand it, and retrieves related information. + Spell check is AI. The software program or chunk of code that checks the text for spelling errors is the rational agent. It’s goal is to find errors and maximize your text’s accuracy. It perceives what you are typing and compares the words to its knowledge base to decide if each word is spelled correctly. Its action is the red squiggly. These technologies have been around for decades! Research in AI has been going on since the 50’s. It’s just now becoming common place in everyday life and is becoming more impressive.
7. And this is just in Europe. I hardly ever hear about numbers that big from that long ago. Data still considers to grow along this exponential curve. “Let’s consider the beginning of the modern era of information. With the advent of the printing press in the 1400s we have an explosion of information — the first democratizing event around access that made it possible for humans everywhere to start learning.” http://news.microsoft.com/features/democratizing-ai/#sm.00000m3p4fmfl1e0bznn1xl9z26it#fpmWezjp3vR836Hq.97 Image: https://commons.wikimedia.org/wiki/File:European_Output_of_Printed_Books_ca._1450%E2%80%931800.png
8. “Access to information has only spread from there. Every walk of life has changed because of our ability to create knowledge and distribute knowledge.” Now we get numbers like that everyday. And this is actually from 2010! And they’re growing exponentially. Updated numbers: + 2,311 Skype calls every second + 7,378 Tweets sent every second + 38,812 GB of Internet traffic every second + 56,765 Google searches every second + 133,401 YouTube videos viewed every second + 2,531,937 Emails sent every second (now that’s some Office 365 data to play with!) http://www.internetlivestats.com/one-second/ Despite all of this data, “one thing has remained constant and scarce: time.” http://news.microsoft.com/features/democratizing-ai/#sm.00000m3p4fmfl1e0bznn1xl9z26it#fpmWezjp3vR836Hq.97 Image: https://www.good.is/infographics/the-world-of-data-we-re-creating-on-the-internet
9. Despite all of this data, “one thing has remained constant and scarce: time.” Problem: Too much data, too little time. http://news.microsoft.com/features/democratizing-ai/#sm.00000m3p4fmfl1e0bznn1xl9z26it#fpmWezjp3vR836Hq.97 Image: https://cdn.vectorstock.com/i/composite/78,49/black-wall-clock-vector-657849.jpg
10. Solution: AI can help us save time and have a better understanding of the world. Make optimal decisions. Predict the future. “It’s about helping everyone achieve more — humans and machines working together to make the world a better place.” http://news.microsoft.com/features/democratizing-ai/#sm.00000m3p4fmfl1e0bznn1xl9z26it#fpmWezjp3vR836Hq.97
11. Text: http://news.microsoft.com/features/democratizing-ai/#sm.00000m3p4fmfl1e0bznn1xl9z26it#fpmWezjp3vR836Hq.97 Image: https://ignite.microsoft.com/Images/MSIgnite_Atlanta_Skyline_Jan20_TW.PNG
12. http://news.microsoft.com/features/democratizing-ai/#5t3OAVLgAEsIcJAV.99 Now We’re going to go over these four categories Microsoft is focusing on.
13. http://news.microsoft.com/features/democratizing-ai/#5t3OAVLgAEsIcJAV.99 My Favorite category. Natural language interfaces are going to be increasingly more common. We’ll be talking to all kinds of devices eventually. Anyone played with the Amazon Echo? You can now talk to lamps.
14. What are agents? They’re Intelligent Bots, or Intelligent Conversations-as-a-Platform. Conversational platforms are the next frontier in human interaction models – rather than having hundreds of apps on your phone with which you interact for different things, you just go to one single conversational platform of your choice and talk to agents or bots that live in that platform. You can design bots for customer service or shopping or arbitrary other services that you need to deliver. Text: https://blogs.technet.microsoft.com/machinelearning/2016/10/05/microsoft-machine-learning-data-science-summit-and-ignite-recap/ Image: https://www.windowscentral.com/sites/wpcentral.com/files/styles/larger/public/field/image/2016/03/conversations-as-a-platform.jpg?itok=sfS8NaSh
15. https://www.projectmurphy.net/ What if the presidential candidates were Disney princesses?
16. http://news.microsoft.com/features/democratizing-ai/#5t3OAVLgAEsIcJAV.99
17. Was anyone at Ian’s talk at this meetup a couple months ago? He gave a great overview of the Microsoft Graph. When it comes down to building applications, the data is key and this set of data is glorious. So many possible applications with all that data. Things like you see Office Delve doing are only some examples of what’s possible. There are plenty more custom solutions you can build on top of the same data.
18. “In Office 365, My Analytics is like a fitness tracker for your workday, showing how you’re spending your time informed by the Microsoft Graph and powered by AI.” https://news.microsoft.com/features/democratizing-ai/ Image: https://cdn-mspoweruser.netdna-ssl.com/wp-content/uploads/2016/09/MYANALYTICS_FINAL.gif
19. http://news.microsoft.com/features/democratizing-ai/#5t3OAVLgAEsIcJAV.99
20. Like IBM, Microsoft is also a part of the Cognitive Era. Instead of Watson Services, Microsoft has the Cognitive Services to drive Cognitive Computing or Intelligent Applications. These can be used to build human-like AI into your apps. So many options! Recommendations API is a big part of Delve and is a good service to apply to collaboration problems. Demo: https://www.microsoft.com/cognitive-services Emotion API with presidential candidate’s pictures: Everyone’s worst nightmare https://i.imgflip.com/zjag1.jpg Donald Clinton http://cdn.ebaumsworld.com/mediaFiles/picture/202553/85145592.jpg Who survives? America https://img1.steemit.com/0x0/http://scalar.usc.edu/works/memes-1/media/trump:clinton%20meme.jpg
21. http://news.microsoft.com/features/democratizing-ai/
22. “Today we have a global, hyperscale, cloud infrastructure that we continue to improve across many dimensions – performance, scale and increasing richness and sophistication of higher level services to enable scenarios that simply were not possible before. We’ve added GPUs to that cloud to deliver the highest performance cloud available.   All of that is available today at unprecedented scale. But we’re not stopping there. Azure is now the world’s first AI supercomputer. Put another way, we’re looking post-Moore’s-Law — and solving for the issue of Moore’s Law running out of steam. ” Microsoft helped progress the hardware. CPU’s were optimized for bitwise operations and basic math. GPU’s then were optimized for linear algebra problems, common in image and video processing so that’s why we use them for graphics. The next-level is FPGA, which allows us to manipulate the hardware so it is optimized for custom operations. https://en.wikipedia.org/wiki/Field-programmable_gate_array “By adding this super AI technology to the cloud, we can do amazing things. Consider translation as one example. Using just a single node of our FPGA fabric we can translate War and Peace, all 1440 pages, from Russian to English in just two and a half seconds. If we take the entire capability today, the AI supercomputer can translate all of Wikipedia— which printed and stacked on end would stand a quarter mile high — in less than one tenth of a second, less time than it takes you to blink once. The same set of FPGA nodes on our fabric could also translate the Library of Congress, about 38 million books, in 76 seconds — about the time it takes you to walk and get a cup of coffee at work.” – Satya http://news.microsoft.com/features/democratizing-ai/
23. As a fully managed big data and advanced analytics suite, Cortana Intelligence is a powerful solution to transform your data into intelligent action. This Suite exposes many of the same technologies Microsoft uses to create intelligence in the tools we use everyday. https://www.microsoft.com/en-us/cloud-platform/what-is-cortana-intelligence-suite Here are the products that make up the Cortana Intelligence Suite. They have a lot going on! The suite covers data management, big data, machine learning, cognitive computing, and data visualization. + Orchestrate data movement on a fully managed, end-to-end platform. + Design and publish predictive models with Azure Machine Learning, use Azure HDInsight to analyze data in Storm and Spark for Hadoop environments, integrate your code from R or Python, and analyze any kind or any size of data you need with Azure Data Lake Analytics and Azure Stream Analytics. Plus, use Microsoft Power BI to create rich visualizations that bring your data to life. + Explore Cognitive Services and learn how to enable natural and contextual interactions in your apps. https://www.microsoft.com/en-us/cloud-platform/what-is-cortana-intelligence-suite
24. This is the concept of augmented or extended intelligence. We are humans collaborating with machines, allowing us to do more, better, faster. There are many intelligent tools already available to all of us out there. Microsoft is doing their part to build intelligent apps and services for us. These are only a small sample of what is ahead. There are many new applications and systems left for us to build! https://news.microsoft.com/speeches/satya-nadella-microsoft-ignite-2016 http://news.microsoft.com/features/democratizing-ai/#5t3OAVLgAEsIcJAV.99
25. Even innovation can be exponential. Text: https://www.microsoft.com/en-us/research/event/faculty-summit-2016/ Image: https://www.microsoft.com/en-us/research/wp-content/uploads/2016/05/Faculty-Summit-Day-2-007.jpg
26. “The Intelligent Revolution is truly beginning.” ~ Satya Nadella
27. Deck can be found online at: http://www.slideshare.net/PaulPrae/ai-everywhere-how-microsoft-is-democratizing-ai
28. I love AI. I’m currently taking courses at Georgia Tech in pursuit of the OMSCS. My AI studies began about 8 years ago at UGA. Deck can be found online at: http://www.slideshare.net/PaulPrae/ai-everywhere-how-microsoft-is-democratizing-ai
29. Deck can be found online at: http://www.slideshare.net/PaulPrae/ai-everywhere-how-microsoft-is-democratizing-ai