Large Patterns Make Great Symbols: An Example of Learning from Example
@inproceedings{Kanerva1998LargePM, title={Large Patterns Make Great Symbols: An Example of Learning from Example}, author={P. Kanerva}, booktitle={Hybrid Neural Systems}, year={1998} }
We look at distributed representation of structure with variable binding, that is natural for neural nets and that allows traditional symbolic representation and processing. The representation supports learning from example. This is demonstrated by taking several instances of the mother-of relation implying the parent-of relation, by encoding them into a mapping vector, and by showing that the mapping vector maps new instances of mother-of into parent-of. Possible implications to AI are… CONTINUE READING
Figures and Topics from this paper
Figures
28 Citations
Analogical mapping and inference with binary spatter codes and sparse distributed memory
- Computer Science
- The 2013 International Joint Conference on Neural Networks (IJCNN)
- 2013
- 28
- Highly Influenced
- PDF
Resonator networks for factoring distributed representations of data structures
- Computer Science
- ArXiv
- 2020
- 1
- PDF
Analogical Mapping with Sparse Distributed Memory: A Simple Model that Learns to Generalize from Examples
- Computer Science
- Cognitive Computation
- 2013
- 14
- PDF
Some approaches to analogical mapping with structure-sensitive distributed representations
- Computer Science
- J. Exp. Theor. Artif. Intell.
- 2004
- 18
Imitation of honey bees’ concept learning processes using Vector Symbolic Architectures
- Computer Science
- BICA 2015
- 2015
- 21
Resonator Networks, 1: An Efficient Solution for Factoring High-Dimensional, Distributed Representations of Data Structures
- Computer Science, Medicine
- Neural Computation
- 2020
- 1
- PDF
Randomly connected sigma–pi neurons can form associator networks
- Medicine, Computer Science
- Network
- 2000
- 30
References
SHOWING 1-10 OF 16 REFERENCES
Distributed representations of structure: A theory of analogical access and mapping.
- Computer Science
- 1997
- 922
- PDF
From simple associations to systematic reasoning: A connectionist representation of rules, variables and dynamic bindings using temporal synchrony
- Psychology
- 1993
- 741
- PDF
Mapping Part-Whole Hierarchies into Connectionist Networks
- Computer Science
- Artif. Intell.
- 1990
- 351
- Highly Influential
- PDF