Introducing the Numenta HTM Challenge
Numenta has held five hackathons over the past several years to engage our community of dedicated and passionate HTM enthusiasts. It’s been a great time for lots of people involved. We’ve grown together and created some really interesting things!
The one consistent complaint I’ve gotten from hackathon attendees is that there just wasn’t enough time to complete their projects. In response to this feedback and our desire to incubate more complete HTM projects, we have completely changed the structure and format of our hackathons.
Introducting the Numenta HTM Challenge!
The Numenta HTM Challenge is an online contest open for submissions today and running until November 14th. Participants must come up with ideas for real-world applications of HTM technology and submit them for approval before starting work. This ensures the problem being solved is applicable to HTM, and that the data being analyzed is adequate for HTM. Once a project has been approved, hackers have until November 6th to work on it and submit a demo video for judging.
Onsite Event Nov 14
This Challenge can be completed entirely online, but we encourage you to try to attend the Onsite Event that culminates the Challenge on November 14 in Redwood City, California. At this Onsite Event, all demonstration videos will be viewed by a judging panel and a live audience. Judges will get a chance to comment and ask questions to submission authors (either live or over the phone). At the end of the event, we’ll announce the winners and cash prizes will be awarded!
In addition to judging, there will also be at least two educational sessions by Numenta team members Subutai Ahmad and Jeff Hawkins. They will be talking about the history and evolution of HTM algorithms and some details about new algorithm development, respectively.
Temporal Pooling (Jeff Hawkins)
Temporal pooling is an important aspect of HTM theory. It refers to how representations get more stable as sensory data moves from region to region ascending the cortical hierarchy. It plays an important role in inference, feedback, and motor control. Our understanding of how temporal works has been refined a couple of times since the original HTM white paper was published. In this talk I will review the basic requirements of temporal pooling and introduce a new model for temporal pooling, one that is more robust that previous versions. I will also discuss how we think this new temporal pooling model is implemented in neurons in the neocortex.
Temporal Memory of HTM: A Retrospective (Subutai Ahmad)
Did you realize that the development of HTM algorithms at Numenta has been going on for over 10 years? Subutai (who has seen it all) will step you through the sequence of HTM developments, from our very first demos, algorithms and products, to our current research on cortical algorithms. Come and see what we have learned, and how our past informs our future.
You don’t have to participate in the Challenge to attend the Onsite Event! Maybe you just want to come see the latest presentations from Numenta or watch the Challenge demonstration judging. That’s great! We welcome you to mingle with us HTM enthusiasts.
And as long as you’ll be in the area, there is a Community Event being planned on the Friday before the Onsite Event. I hope you’ll attend just to meet the rest of the HTM community. This event is run by the NuPIC community, for the NuPIC community. A schedule is in the works.
Help us build the future of Machine Intelligence!
We believe that HTM is the future of machine intelligence. This is a great chance for you to get involved and help us move this important technology forward. I hope you’ll consider being a part of this event in some way.