Updated: Aug 04, 2016, 5:00pm PST
Welcome to the 3rd community-hosted HTM (Hierarchical Temporal Memory) Meetup.
Meet HTM hackers, AI researchers, Entrepreneurs and enthusiasts working in the
field of Artificial Intelligence. See below for a brief agenda.
As always we have a special focus on lightning talks where you get to talk about
your latest work. Sign up for a lightning talk if you plan to present. (Slots
are limited, make sure you sign up fast).
6:00 – 7:00: Welcome, Sign In and Networking
7:00 – 7:10: About our Host (A message from our host for the day)
7:10 – 7:20: State of HTM Open Source
(Matt Taylor, HTM Community Manager @ Numenta)
7:20 – 7:30: Message from Numenta
(Christy Maver, Director of Marketing @ Numenta)
7:30 – 7:40: Current HTM Theory thought process (TBD)
- 7:40 – 9:00: Lightning Talks and Demos
Lightning Talks and Demos
Two Extensions to HTM Engine – Ryan Mccall: an overview of HTM engine,
describe the changes, and demo how to use them.
HTM SCHOOL LIVE (SDRs and Spatial Pooling) – Matt Taylor: Matt has been
creating several YouTube videos about HTMs. He will talk in detail about
Sparse Distributed Representations and Spatial Pooling.
Computational properties of the HTM spatial pooler – Yuwei Cui (Research
Engineer @ Numenta): Talk about the HTM spatial pooler and update on state
of current research.
- A Comparison of Popular AI Technologies – Chandan Maruthi: We have often been
asked for a comparison of different algorithms used in AI. Chandan will cover
some of the key aspects of traditional AI methods, including HTM’s.
To sign-up for a demo/lighting talk email:
What is HTM?
Hierarchical Temporal Memory (HTM) is an online machine learning model developed
by Numenta, Inc. that models some of the structural and algorithmic properties
of the neocortex. HTM is a biomimetic model based on the memory-prediction
theory of brain function described by Jeff Hawkins in his book, On Intelligence.
HTM is a method for discovering and inferring the high-level causes of observed
input patterns and sequences, thus building an increasingly complex model of the
More information about HTMs: