A neural net for reconstruction of multiple curves with a visual grammar

@article{Mjolsness1991ANN,
  title={A neural net for reconstruction of multiple curves with a visual grammar},
  author={Eric Mjolsness and Anand Rangarajan and Charles Garrett},
  journal={IJCNN-91-Seattle International Joint Conference on Neural Networks},
  year={1991},
  volume={i},
  pages={615-620 vol.1}
}
A neural net has been derived for reconstructing a set of curves from ungrouped dot locations. The network performs Bayesian inference on a visual grammar, which serves as a probabilistic model of the image formation process, by means of a quadratic matching objective function. The steps involved in the derivation are: (1) formulate a stochastic grammar; (2) derive its probability distribution on images, along with the partition function which is a configuration space integral over both… 

Figures and Tables from this paper

Visual grammars and their neural networks
  • E. Mjolsness
  • Computer Science
    Defense, Security, and Sensing
  • 1992
TLDR
The grammatical method of neural net design allows domain knowledge to enter from all levels of the grammar, including `abstract' levels remote from the final image data, and may permit new kinds of learning as well.
Bayesian Inference on Visual Grammars by Neural Nets that Optimize
We exhibit a systematic way to derive neural nets for vision problems It involves formulating a vision problem as Bayesian inference or decision on a comprehensive model of the visual domain given by
Multiscale modeling of developmental processes
TLDR
This work describes a very simple mathematical idealization of these three levels which combines the crossover search method of genetic algorithms with the developmental models used in the previous work on “genetic” or “recursively generated” artificial neural nets.
Genetic Algorithms for Genetic Neural Nets.
TLDR
A very simple mathematical idealization of these three levels of biological development which combines the crossover search method of genetic algorithms with the developmental models used in previous work on 'genetic' or 'recursively generated' artificial neural nets is described.
Visual Grammars and Their Neural Nets
TLDR
A systematic way to derive neural nets for vision problems by formulating a vision problem as Bayesian inference or decision on a comprehensive model of the visual domain given by a probabilistic grammar.

References

SHOWING 1-3 OF 3 REFERENCES
A New Method for Mapping Optimization Problems Onto Neural Networks
TLDR
A novel modified method for obtaining approximate solutions to difficult optimization problems within the neural network paradigm is presented, which considers the graph partition and the travelling salesman problems and exhibits an impressive level of parameter insensitivity.
Optimization in Model Matching and Perceptual Organization
TLDR
This work casts vision problems as inexact graph matching problems, formulate graph matching in terms of constrained optimization, and use analog neural networks to perform the optimization.
Pattern recognition by labeled graph matching