Engineering General Intelligence, Part 2: The CogPrime Architecture for Integrative, Embodied AGIThe work outlines a detailed blueprint for the creation of an Artificial General Intelligence system with capability at the human level and ultimately beyond, according to the Cog Prime AGI design and the Open Cog software architecture. |
What people are saying - Write a review
We haven't found any reviews in the usual places.
Contents
| 3 | |
2 Knowledge Representation Using the Atomspace | 31 |
3 Representing Procedural Knowledge | 55 |
Part II The Cognitive Cycle
| 73 |
4 Emotion Motivation Attention and Control | 74 |
5 Attention Allocation | 93 |
6 Economic Goal and Action Selection | 126 |
7 Integrative Procedure Evaluation | 135 |
18 Adaptive Integrative Inference Control | 309 |
19 Pattern Mining | 331 |
20 Speculative Concept Formation | 341 |
Part VI Integrative Learning
| 353 |
21 Dimensional Embedding | 354 |
22 Mental Simulation and Episodic Memory | 363 |
23 Integrative Procedure Learning | 369 |
24 Map Formation | 390 |
Part III Perception and Action
| 141 |
8 Perceptual and Motor Hierarchies | 143 |
9 Integrating CogPrime with a Compositional Spatiotemporal Deep Learning Network | 162 |
10 Making DeSTIN Representationally Transparent | 173 |
11 Bridging the SymbolicSubsymbolic Gap | 189 |
Part IV Procedure Learning
| 210 |
12 Procedure Learning as Program Learning | 211 |
13 Learning Procedures via Imitation Reinforcement and Correction | 217 |
14 Procedure Learning via Adaptively Biased Hillclimbing | 227 |
15 Probabilistic Evolutionary Procedure Learning | 239 |
Part V Declarative Learning
| 272 |
16 Probabilistic Logic Networks | 275 |
17 Spatiotemporal Inference | 292 |
Part VII Communication Between Human and Artificial Minds
| 408 |
25 Communication Between Artificial Minds | 409 |
26 Natural Language Comprehension | 423 |
27 Language Learning via Unsupervised Corpus Analysis | 465 |
28 Natural Language Generation | 487 |
29 Embodied Language Processing | 496 |
30 Natural Language Dialogue | 515 |
Part VIII From Here to AGI
| 526 |
31 Summary of Argument for the CogPrime Approach | 529 |
References | 549 |
| 557 | |
Other editions - View all
Common terms and phrases
achieve action agent AGI system algorithm approach architecture Atlantis Atoms AtomSpace attention allocation backward chaining basic behavior centroids clusters cognitive processes CogPrime system CogPrime’s combination Combo tree complex computational concept ConceptNodes context corpus corresponding create CSDLN defined described DeSTIN dynamics ECAN embedding embodied Evaluation EvaluationLink evolutionary example execution ExecutionLink fitness function formalism FrameNet fuzzy goal graph HebbianLinks heuristic hierarchical hillclimbing human human-level implementation important Inheritance InheritanceLink input instance integration involving knowledge knowledge representation language learning linguistic Link Grammar link types logical machine memory MindAgents MOSES multiple NLGen nodes OpenCog optimization parsing pattern mining perception PLN inference predicate PredicateNode probabilistic probability problem procedural knowledge procedure learning reasoning relationships RelEx represent representation rules schema SchemaNode schemata semantic sentence similar simple sort space spatiotemporal specific structure subtrees supervised learning syntactic Thinking Machines truth value Ubergoal variables virtual world Word Grammar
Bibliographic information
| Title | Engineering General Intelligence, Part 2: The CogPrime Architecture for Integrative, Embodied AGI Volume 6 of Atlantis Thinking Machines |
| Authors | Ben Goertzel, Cassio Pennachin, Nil Geisweiller |
| Edition | illustrated |
| Publisher | Springer, 2014 |
| ISBN | 9462390304, 9789462390300 |
| Length | 562 pages |
| Subjects | › › Computers / Artificial Intelligence / General Computers / Information Technology |
| Export Citation | BiBTeX EndNote RefMan |