Compositional Constructive Induction : Discovering Topological Features of Environmental Changes from Vision Data

@inproceedings{Prabhakar1999CompositionalCI,
  title={Compositional Constructive Induction : Discovering Topological Features of Environmental Changes from Vision Data},
  author={Sattiraju Prabhakar},
  year={1999}
}
The autonomous agents need to build models of environment in order to predict the consequences of their actions. In order to do this, discovering features that can measure the topological changes in the environment is a first and important step. The requirements of this discovery task includes that the features are constructed from vision data, applicability of features to new environments and flexibility of features to adapt to new examples. Compositional Constructive Induction method… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-9 of 9 references

Discovery as autonomous learning from the environment

Machine Learning • 1993
View 3 Excerpts
Highly Influenced

Qualitative Analysis of Distributed Physical Systems with Applications to Control Synthesis

C. Bailey-Kellog, F. Zhao
Proceedings of Fifteenth National Conference on Artificial Intelligence • 1998
View 1 Excerpt

Similar Papers

Loading similar papers…