Epstein Secrets

arding the representation of knowledge using attractor neural nets. It is a mix of well-established fact with more speculative material. 13.4.1 The Hopfield neural net model Hopfield networks Iliop821 are attractor neural networks often used as associative memories. A Hopfield network with N neurons can

tation of glocal memory in attractor neural net systems • Chapter 23 presents Glocal Economic Attention Networks (ECANs), rough analogues of glocal Hopfield nets that play a central role in CogPrime. Our hypothesis of the potential general importance of glocality as a property of memory, systems (beyond

moved without significantly impacting the net- work's capacity or dynamics. Our experimental work uses sparse Hopfield networks. 13.4.1.1 Palimpsest Hopfield nets with a modified learning rule In JSV99J a new learning rule is presented, which both increases the Hopfield network capacity and turns it into

ference problems, from the CogPrime perspective, is that assuming one provides the inference system with an appropriate set of perceptual and motor ConceptNodes and Schemallodes, the chains of inference involved are short. They involve about a dozen inferences, and this means that the search tree of possible

garding the representation of knowledge using attractor neural nets. It is a mix of well-established fact with more speculative material. 13.4.1 The Hopfield neural net model Hopfield networks [Hop82] are attractor neural networks often used as associative memories. A Hopfield network with N neurons can b

ntation of glocal memory in attractor neural net systems e Chapter 23 presents Glocal Economic Attention Networks (ECANs), rough analogues of glocal Hopfield nets that play a central role in CogPrime. Our hypothesis of the potential general importance of glocality as a property of memory systems (beyond j

moved without significantly impacting the net- work’s capacity or dynamics. Our experimental work uses sparse Hopfield networks. 13.4.1.1 Palimpsest Hopfield nets with a modified learning rule In [SV99] a new learning rule is presented, which both increases the Hopfield network capacity and turns it into

inference problems, from the CogPrime perspective, is that assuming one provides the inference system with an appropriate set of perceptual and motor ConceptNodes and SchemaNodes, the chains of inference involved are short. They involve about a dozen inferences, and this means that the search tree of possible P

some of the properties that the above ECAN equations display when we use an ECAN defined by them as an associative memory network in the manner of a Hopfield network. We consider a situation where the ECAN is supplied with memories via a "training" phase in which one imprints it with a series of binary

orks Economic Attention Networks (ECANs) are dynamical systems based on the propagation of STI and LTI values. They are similar in many respects to Hopfield nets, but are based on a different conceptual foundation involving the propagation of amounts of (conserved) currency rather than neural-net activa

MemberLinks. This is in accordance with the notion of glocal memory, in the language of which the HPAN attractors are the maps and the corresponding ConceptNodes are the keys. Put simply, when a HPAN attractor is recognized, MemberLinks are created between the HPAN nodes comprising the main body of the attra

icitly. In general, entropy maximization principles provide the foundation for learning systems such as (hidden) Markov models, Markov networks and Hopfield neural networks, and they connect indirectly with Bayesian probability based analyses. However, the actual task of maximizing the entropy is an NP-h

s of word sense creation. Suppose we have a WordNode W that has ReferenceLinks to a number of different Con- ceptNodes. A common case is that these ConceptNodes fall into clusters, each one denoting a "sense" of the word. The clusters are defined by the following relationships: 1. ConceptNodes within a clus

FTA00623877 102 5 A Generic Architecture of Human-Like Cognition touch and smell (the latter being better modeled as something like an asymmetric Hopfield net, prone to frequent chaotic dynamics ILIAV*051) - these may also cross-connect with each other and with the more hierarchical perceptual subnetw

Knowledge in the Atomspace. A simple example of implicit knowledge in the Atomspace. The "chicken" and "food" concepts are represented by "maps" of ConceptNodes interconnected by HebbianLinks, where the latter tend to form between Con- ceptNodes that are often simultaneously important. The bundle of links bet

RSIGHT_013017 102 5 A Generic Architecture of Human-Like Cognition touch and smell (the latter being better modeled as something like an asymmetric Hopfield net, prone to frequent chaotic dynamics [LLW~05]) — these may also cross-connect with each other and with the more hierarchical perceptual subnetwork

t Knowledge in the Atomspace. A simple example of implicit knowledge in the Atomspace. The "chicken" and "food" concepts are represented by "maps" of ConceptNodes interconnected by HebbianLinks, where the latter tend to form between Con- ceptNodes that are often simultaneously important. The bundle of links bet