 So the way I like I like to look at our initiative is you know, we want to take advantage of all the interactivity that's Exploding and computing and structure and use them to structure learning experiences that are deeply immersive and deeply engaging So the cognitive science part comes where you know, we try to figure out You know what's actually happening in the brain as a function of all these emerging workloads and what does effective learning look like, right? So so the signature initiator that we have is to use a computer to teach people Using what we call an intelligent children system where Watson acts as an intelligent shooter and works with a person in a very personalized fashion So so our global initiative essentially works on a whole series of such technologies they're all deeply infused with AI techniques like machine learning and natural language processing and There's a little bit of cock-into-science and a flavor of cock-into-science behind what we do So we are attempting to mimic the best practices of human tutoring Right the gold standard will always remain one-on-one human to human tutoring The whole idea here is an intelligent shooting system as a computing system that works autonomously with learners So there is no human intervention. It's basically pretending to be the the teacher itself and it's working with with the learner and So what we're attempting to do is we're attempting to basically put conversational systems systems that understand You know human conversation and dialogue and and we're trying to build a system that that in a in a very natural way interacts with people through conversation and The system basically has a the ability to ask questions to answer questions To know who you are and where you are in your learning journey what you're struggling with what you're strong on Right and it will personalize its pedagogy to you. We have a fully conversation-enabled chatbot Chatbot is kind of a you know doing it a little bit less justice than I'd hope but it's a fully conversation-enabled tutoring system that's working with students in college and in you know in lifelong Vocational courses And it's attempting to teach them, you know their own topics that they're trying to master at their own pace and it's there as a non-judgmental 24-7 tutor that they can ask all kinds of questions to and it will also answer all the questions that they have and We're doing this in a partnership with Pearson, which we formed late last year and be announced And we we hope to cover a variety of disciplines that are taught in four-year colleges anywhere from psychology all the way to environmental sciences and and physics and astronomy by the time we're done At the heart of our approach is an ability for computers to semantically Understand language, right? It's a semantic understanding, but it's not a human level understanding there's a there's a fairly deep understanding of You know, what kinds of questions you're asking for instance You can you can phrase a question in any number of ways the way people do and the system still understands What the gist of the question is and it will retrieve the right answer for you? similarly it can it can ask you questions and You will provide your own responses in your own language and it will figure out if you've covered what it was looking for in an answer And and this whole exchange is also deeply personalized So it will figure out what the right question to surface to you is Based on what you've actually done so far in that particular course, right? So so to address the formal question it's There's there's basically two major components behind it There's a natural language understanding system and a machine learning system that's that's trying to figure out where you are in your learning journey and and what the appropriate You know intervention is for you and the land natural language system and enables this interaction That's very rich and and conversation based Where you can basically have a human like conversation with it And to a large extent it will try to understand and retrieve the right things for you and again The most important thing is that we will set The expectations appropriately and we have appropriate exit criteria for when the system doesn't actually understand what you're trying to do The learning models are basically a whole bunch of machine learning models where we're taking a lot of data So depending on how you know instrumented the learning experience is We can spend time looking at for instance. How many times have you attempted a question? How many times have you tried to watch a video? How many times have you rewound a video? How long have you spent on a learning object, right? All of these are indicators to us about You know your state of confidence or you know mastery over a particular domain, right? And then based on that the system is turning around and recommending something else to do for you, right? The center thing is basically analytics driven. It's all data driven the evidence is data driven and It's based on what we think has worked in the past and and at the same time We're also marrying this with the with the rich ability to understand where the learners are through their own language