Connections and symbols
On Intelligence
SAL: an explicitly pluralistic cognitive architecture
Journal of Experimental & Theoretical Artificial Intelligence - Pluralism and the Future of Cognitive Science
Perspectives of Neural-Symbolic Integration
Perspectives of Neural-Symbolic Integration
Proceedings of the 2008 conference on Artificial General Intelligence 2008: Proceedings of the First AGI Conference
BioNLP '06 Proceedings of the Workshop on Linking Natural Language Processing and Biology: Towards Deeper Biological Literature Analysis
Extracting reduced logic programs from artificial neural networks
Applied Intelligence
Deep Spatiotemporal Feature Learning with Application to Image Classification
ICMLA '10 Proceedings of the 2010 Ninth International Conference on Machine Learning and Applications
Temporal restricted Boltzmann machines for dependency parsing
HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: short papers - Volume 2
Newton-Type Algorithms for Dynamics-Based Robot Movement Optimization
IEEE Transactions on Robotics
The Soar Cognitive Architecture
The Soar Cognitive Architecture
Integrating feature selection into program learning
AGI'13 Proceedings of the 6th international conference on Artificial General Intelligence
Integrating deep learning based perception with probabilistic logic via frequent pattern mining
AGI'13 Proceedings of the 6th international conference on Artificial General Intelligence
A cognitive architecture based on dual process theory
AGI'13 Proceedings of the 6th international conference on Artificial General Intelligence
Hi-index | 0.00 |
Bridging the gap between symbolic and subsymbolic representations is a --- perhaps the --- key obstacle along the path from the present state of AI achievement to human-level artificial general intelligence. One approach to bridging this gap is hybridization --- for instance, incorporation of a subsymbolic system and a symbolic system into a integrative cognitive architecture. Here we present a detailed design for an implementation of this approach, via integrating a version of the DeSTIN deep learning system into OpenCog, an integrative cognitive architecture including rich symbolic capabilities. This is a "tight" integration, in which the symbolic and subsymbolic aspects exert detailed real-time influence on each others' operations. An earlier technical report has described in detail the revisions to DeSTIN needed to support this integration, which are mainly along the lines of making it more "representationally transparent," so that its internal states are easier for OpenCog to understand.