Implications of Recursive Distributed Representations

  title={Implications of Recursive Distributed Representations},
  author={Jordan B. Pollack},
I will describe my recent results on the automatic development of fixed-width recursive distributed representations of variable-sized hierarchal data structures. One implication of this work is that certain types of AI-style datastructures can now be represented in fixed-width analog vectors. Simple inferences can be performed using the type of pattern associations that neural networks excel at. Another implication arises from noting that these representations become self-similar in the limit… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.


Publications citing this paper.


Publications referenced by this paper.
Showing 1-10 of 25 references

Finding Structure in Time

Cognitive Science • 1990
View 1 Excerpt

Recursive Distributed Representations

Artif. Intell. • 1990
View 2 Excerpts

Intelligence as emergent behavior ; or , the songs of eden

W. D. Hillis
Daedelus • 1988
View 1 Excerpt

Nonlinear Signal Processing using Neural Networks : Prediction and system modeling

A. S. Lapedes, R. M. Farber
Biological Cybernetics , To appear • 1988
View 2 Excerpts

Representing PartWhole hierarchies in connectionist networks

G. Hinton
Proceedings of the Tenth Annual Conference of the Cognitive Science Society . Montreal • 1988

Weight Matrix = Pattern of Activation : Encoding Semantic Networks as Distributed Representations in DUAL , a PDP architecture

M. G. Dyer, M. Flowers, Y. A. Wang
View 1 Excerpt

Cascaded Back Propagation on Dynamic Connectionist Networks

J. B. Pollack
Proceedings of the Ninth Conference of the Cognitive Science Society • 1987
View 2 Excerpts

Dimensionality Reduction and Constraint in Later Vision

E. Saund
Proceedings of the Ninth Annual Conference of the Cognitive Science Society • 1987
View 1 Excerpt

Similar Papers

Loading similar papers…