Epstein Secrets

th Values and Attention Values 255 13.4 Knowledge Representation via Attractor Neural Networks 256 EFTA00623773 xviii Contents 13.4.1 The Hopfield neural net model 256 13.4.2 Knowledge Representation via Cell Assemblies 257 13.5 Neural Foundations of Learning 258 13.5.1 Hebbian Learni

ve pattern recognition as well as static pattern recognition. Audition likely utilizes a similar hierarchy. Olfaction may use something more like a Hopfield attractor neural network, as described in Chapter 13. The networks corresponding to different sense modalities have multiple cross-linkages, more a

rithms carrying out separate functions, encapsulated in black boxes and communicating results with each other." For instance, PolyScheme, ACT-R and CLARION all display this "modularity" property to a significant extent. These architectures lack the rich, real-time interaction between the intents/ dynam

w several hybrid architectures in more detail, focusing most deeply on LIDA and MicroPsi which have been directly inspirational for CogPrime. 4.5.1 CLARION Ron Sun's CLARION architecture (see Figure 4.9) is interesting in its combination of symbolic and neural aspects - a combination that is used in a

e eee eee 255 13.4 Knowledge Representation via Attractor Neural Networks ................... 256 HOUSE_OVERSIGHT_012913 xviii Contents 13.4.1 The Hopfield neural net model ..............0..0 022 e eee 256 13.4.2 Knowledge Representation via Cell Assemblies .................2.05- 257 13.5 Neural Foundati

tive pattern recognition as well as static pattern recognition. Audition likely utilizes a similar hierarchy. Olfaction may use something more like a Hopfield attractor neural network, as described in Chapter 13. The networks corresponding to different sense modalities have multiple cross-linkages, more at

intelligence will involve a combination of symbolic and non-symbolic processing.” A few of the more important hybrid cognitive architectures are: ¢ CLARION [SZ04] is a hybrid architecture that combines a symbolic component for reason- ing on “explicit knowledge” with a connectionist component for managin

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

chematics and production rules or other similar constructs, is that in CogPrime this level of knowledge representation is not the only important one. CLARION [SZ04], as reviewed above, is an example of a cognitive architecture that uses production rules for explicit knowledge representation and then uses a