Home > Uncategorized > Weekly QuEST Discussion Topics and News, 17 Apr

Weekly QuEST Discussion Topics and News, 17 Apr

QuEST 17Apr 2015:

We have this week a guest speaker – from Penn – Prof Dan Guralnik – He has been part of a Multi-University Research Initiative associated with topics of interest to QuEST.

We propose a self-organizing memory architecture for perceptual experience provably capable of supporting autonomous learning and goal-directed problem solving in the absence of any prior information about the agent’s environment. The architecture is simple enough to ensure (1) a quadratic bound (in the number of available sensors) on space requirements, and (2) a quadratic bound on the time-complexity of the update-execute cycle. At the same time, it is sufficiently complex to provide the agent with an internal representation which is (3) minimal among all representations which account for every sensory equivalence class consistent with the agent’s belief state; (4) capable, in principle, of recovering a topological model of the problem space; and (5) learnable with arbitrary precision through a random application of the available actions. These provable properties — both the trainability and the efficacy of an effectively trained memory structure — exploit a duality between {\it weak poc sets}~ —~ a symbolic (discrete) representation of subset nesting relations~ —~ and {\it non-positively curved cubical complexes}, whose rich convexity theory underlies the planning cycle of the proposed architecture.

news summary (16)

Categories: Uncategorized
  1. No comments yet.
  1. No trackbacks yet.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: