The following videos are officially supported by Numenta. Other community-provided resources can be found on our community content page.
NuPIC Flag-Bearer Matt Taylor instructs on how to execute programmatic swarming and model creation for sine wave data.
The neocortex generates most of our high level behavior and every region in the neocortex has some form of motor output. In this talk I will describe what we know about how the cortex generates behavior and how behavior fits within the framework of Hierarchical Temporal Memory theory. Although we don’t yet have a comprehensive theory of how the neocortex generates behavior we do understand several of the major components giving us hope that a comprehensive theory may be reachable in the near future.
Given at the Computer History Museum in January, 2014.
Chetan Surpur describes the Random Distributed Scalar Encoder used in NuPIC.
Subutai Ahmad, Grok/Numenta VP of Engineering, detailed some aspects of the CLA at our 2013 Fall Hackathon. He discussed an interesting property of SDR’s affecting temporal pooling and hierarchies. The interactive session included a lot of Q&A. Slides.
Matt Taylor did some NLP work before the 2013 Fall Hackathon in order to help others get started doing some work with NuPIC, NLP, and especially the CEPT API for word SDRs. In this presentation, he presents some of his initial progress. Slides.
In this hands-on session, we introduce NuPIC’s Online Prediction Framework (OPF) and demonstrate how one creates models using an OPF client. We set up some live streaming data to pass into the client and watch as NuPIC makes online inferences, learning the changing patterns in the streaming data set. NuPIC and the OPF have been applied to many scenarios and form the foundation for Numenta’s commercial product, Grok. To master NuPIC you will have to become comfortable with concepts such as sparse distributed representations and on-line learning.
The neocortex works on principles that are fundamentally different than traditional computers. In this talk I will describe recent advances in understanding the neocortex and how we are applying them to model millions of high velocity data streams. The talk will start with a description of sparse distributed representations, which are the fundamental units of information in brains. I will then discuss how these representations are learned and how the brain processes them to build predictive models from sensory data. Numenta has built a product called Grok that emulates these capabilities of the neocortex. Grok is being used to understand high velocity machine generated data in many different domains. I will give a brief introduction to Grok and speculate on the future of machine intelligence.
Jeff Hawkins presented the opening keynote address of the 39th International Symposium on Computer Architecture on June 11, 2012 in Portland, OR. In this presentation, Jeff describes sparse distributed representations, and their impact on future computer architectures.
In this screencast, Jeff Hawkins narrates the presentation he gave at a workshop called “From Data to Knowledge: Machine-Learning with Real-time and Streaming Applications.” The workshop was held May 7-11, 2012 at the University of California, Berkeley.
Sparse distributed representations appear to be the means by which brains encode information. They have several advantageous properties including the ability to encode semantic meaning. We have created a distributed memory system for learning sequences of sparse distribute representations. In addition we have created a means of encoding structured and unstructured data into sparse distributed representations. The resulting memory system learns in an on-line fashion making it suitable for high velocity data streams. We are currently applying it to commercially valuable data streams for prediction, classification, and anomaly detection In this talk I will describe this distributed memory system and illustrate how it can be used to build models and make predictions from data streams.
How the brain creates intelligence is viewed by many as the greatest scientific quest of all time. We are living at the time when rapid progress is being made and a comprehensive theory of brain function is emerging. Jeff Hawkins, an inventor, engineer, neuroscientist, author and entrepreneur, presents the big picture of what we know so far and describes recent progress in a core issue: why neurons are arranged as they are in the neocortex, how this arrangement builds models of the world, and how these models make predictions and generate actions. Series: “UC Berkeley Graduate Council Lectures”
Conversations host Harry Kreisler welcomes Jeff Hawkins, founder of both Palm Computing and Handspring and creator of the Redwood Neuroscience Institute, to promote research on memory and cognition. Hawkins traces his intellectual journey focusing on his lifelong passion to develop a theory of the brain. Hawkins explicates the brain’s operating principles and explores the implications of human intelligence for engineering intelligent machines, the goal of his new company Numenta. Series: “Conversations with History”
Jeff Hawkins discusses 3 operating principles of the neocortex and introduces Grok, a predictive modeling product based on those principles.
Rahul Agarwal, from Numenta, introduces how the Cortical Learning Algorithm implementation within NuPIC works.
Treo creator Jeff Hawkins urges us to take a new look at the brain – to see it not as a fast processor, but as a memory system that stores and plays back experiences to help us predict, intelligently, what will happen next.