In the conclusion of our two-part interview with Numenta Co-founder Jeff Hawkins, host Matt Taylor asks Jeff about how HTM sequence memory builds object representations in space through movement. If you missed it, you can listen to Part 1 here.
For educational material regarding the topics discussed in this podcast episode, you have a few options. If you want to be fed the theory, watch HTM School. If you need more details, there are many papers to explore. If you want to talk to others about HTM theory, get involved in our community. For a primer on grid cells, have a look at this interactive blog post. For more on how we think grid cells work within the neocortex, watch Jeff’s recent talk, Does the Neocortex Use Grid Cell-Like Mechanisms to Learn the Structure of Objects?
- [1:16] Different types of grid cells and orientation – what do we need to know?
- [5:17] Border cells
- [6:36] Object representation
- [9:07] Moving and inferring structure, beyond what we can sense
- [11:20] Difference between Cartesian coordinates and grid cells in the brain. Objects are defined by different locations and the only way to get between those locations is through movement.
- [13.38] Displacement transform using grid cells– given two points, how can I establish a vector that says how far apart they are?
- [16.16] Mechanism for movement between locations, different locations in different reference frames