Image recognition and learning in parallel networks

Raghavan, Raghu; Adams, Frank W.; Nguyen, Huu-Thu; Slawny, J.

doi:10.1117/12.19615

Cited by 2 publications

(4 citation statements)

References 5 publications

(8 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have described and compared several methods for learning the parameters of a dynamical system which has been previously shown ([ANRS91], [RANS9O]) to be effective in image recognition. Some of these methods are new and generally useful: however, we have much work left to do.…”

Section: Discussionmentioning

confidence: 99%

“…In this section, we recapitulate previous work ([ RANS9O], [ANRS91]) that summarizes the PCA dynamics, as well as some limiting cases useful for developing learning algorithms.…”

Section: The Pca Dynamical Systemmentioning

confidence: 96%

“…[ RANS9O]). It should however, be apparent, that the application points to new developments in the theory of cellular automata.…”

Section: Interpretation Of the Pca Weightsmentioning

confidence: 99%

“…Conference reports concerning applications to image recognition are available, e.g. in [RANS9O]. Development of the PCA theory, portions of which we quote in the next section, has been submitted for publication elsewhere [ANRS91].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

<title>Image recognition, learning, and control in a cellular automata network</title>

Raghavan¹

1991

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

The theory of control is being widely used in optimization of dynamical systems. Learning algorithms in neural nets or in statistics have, however, seldom used the techniques of control. One reason for this is that the neural network parameters (synaptic weights) are used quasi-statically during processing after a learning phase, while control theory determines an optimal trajectory in time for the parameters. We address this issue in the context of a neural network dynamics that we have introduced in previous publications as part of an image recognition system designed to integrate modeibased and datadriven approaches in a connectionist framework. An important feature of this approach is that recognition must be achieved explicitly through the short-, rather than the long-time behavior of the dynamics of the system. Our dynamics arises naturally from requirements on the system which include: incorporation of prior knowledge such as in inference rules, locality of inferences, and full parallelism. We have shown this system to be effective in image recognition.In this paper, after reviewing the dynamical system, we compare new algorithms for learning the dynamics with Boltzmann-machine-like formulas. We aiso point out some interesting implications of this approach, namely that of a processing strategy that uses a dynamics for the weights as well as the states of the neurons. We conclude by mentioning the difficulties that remain with a control-theoretic strategy.

show abstract

Section: Discussionmentioning

confidence: 99%

“…In this section, we recapitulate previous work ([ RANS9O], [ANRS91]) that summarizes the PCA dynamics, as well as some limiting cases useful for developing learning algorithms.…”

Section: The Pca Dynamical Systemmentioning

confidence: 96%

“…[ RANS9O]). It should however, be apparent, that the application points to new developments in the theory of cellular automata.…”

Section: Interpretation Of the Pca Weightsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

<title>Image recognition, learning, and control in a cellular automata network</title>

Raghavan¹

1991

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

show abstract

A parallel network for visual cognition

Adams¹,

Nguyen²,

Raghavan

et al. 1992

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

The authors describe a parallel dynamical system designed to integrate model-based and data-driven approaches to image recognition in a neural network, and study one component of the system in detail. That component is the translation-invariant network of probabilistic cellular automata (PCA), which combines feature-detector outputs and collectively performs enhancement and recognition functions. Recognition is a novel application of the PCA. Given a model of the target object, conditions on the PCA weights are obtained which must be satisfied for object enhancement and noise rejection to occur, and engineered weights are constructed. For further refinement of the weights, a training algorithm derived from optimal control theory is proposed. System operation is illustrated with examples derived from visual, infrared, and laser-radar imagery.

show abstract

Image recognition and learning in parallel networks

Cited by 2 publications

References 5 publications

<title>Image recognition, learning, and control in a cellular automata network</title>

<title>Image recognition, learning, and control in a cellular automata network</title>

A parallel network for visual cognition

Contact Info

Product

Resources

About