3
Shared Docs
3
Same-Page
5 / 3
Mentions
ing of larger neuronal subnetworks. Then it would be not at all surprising if neurons in the "key" network corre- sponding to a visual concept like "Bill Clinton's face" would be found to respond differentially to the presentation of appropriate images. Yet, it would also be wrong to overinterpret such data as
pletely different images of the ex-president Bill Clinton. Another unit (from a different patient) respond
oing something (perhaps something in the physical world, or perhaps an abstract mental action). The key SMEPH Edge types, using language drawn from Probabilistic Logic Networks (PLN) and elaborated in Chapter 34 below, are as follows: • ExtensionallnheritanceEdge (ExtInhEdge for short: an edge which, linking one Vertex or
ting of larger neuronal subnetworks. Then it would be not at all surprising if neurons in the “key” network corre- sponding to a visual concept like “Bill Clinton’s face” would be found to respond differentially to the presentation of appropriate images. Yet, it would also be wrong to overinterpret such data as i
pletely different images of the ex-president Bill Clinton. Another unit (from a different patient) responde
doing something (perhaps something in the physical world, or perhaps an abstract mental action). The key SMEPH Edge types, using language drawn from Probabilistic Logic Networks (PLN) and elaborated in Chapter 34 below, are as follows: e ExtensionalInheritanceEdge (ExtInhEdge for short: an edge which, linking one Vertex or E
to what we now have on standard machine learning testbeds like UCI (Bache and Lichman, 2013), or computer vision testbeds like CiFAR (Krizhevsky and Hinton, 2009). Project Plan Overview The work required to execute the project proposed here falls into four primary categories: 1. Game-world development
onal and episodic knowledge. Action Orchestrator Runs learned procedures and sends atomic actions to the virtual world to guide parrot behavior. Probabilistic Logic Networks (PIN) Generalizes. extends. combines and improves procedures learned by MOSES. Procedures learned by PLN can be sent back to MOSES to seed new le
Entities connected to both Bill Clinton and Probabilistic Logic Networks

Donald Trump
PERSON
George W. Bush
PERSON
Marc Rich
PERSON
Stephen Hawking
PERSON
Woody Allen
PERSON
Vladimir Putin
PERSONCourtney Wild
PERSON
Lawrence Krauss
PERSON
Vince Foster
PERSON
Earth
LOCATION
Gerald Edelman
PERSONSimpson
PERSON
Edelman
ORGANIZATION
Michael Jordan
PERSON
Ben Goertzel
PERSONOpenCog
ORGANIZATION
Edge Foundation
ORGANIZATIONCogPrime
ORGANIZATION
Joscha Bach
PERSON
Asimov
PERSON