Acquired Structure, Adapted Parameters: Modifications of the Neocognitron

Trotin, Anne; Darbel, Nicolas; Jutand, F.

doi:10.1016/b978-0-444-89178-5.50030-0

Cited by 5 publications

(4 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some researchers tried to build the Neocognitron dynamically (Trotin, et al 1991), in which they take advantage of a feedback signal to evaluate the effect of decreasing threshold (selectivity). However, the detailed mechanism of the feedback signal has never been published, and they confessed that the automatic adjustment of thresholds was difficult in their experimentation (Darbel et al 1991).…”

Section: Introductionmentioning

confidence: 99%

GA-based supervised learning of Neocognitron

Shi

Tan²

2000

Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challeng

View full text Add to dashboard Cite

Supervised learning of Neocognitron is fulfilled by presenting the training patterns, which are mapping to specified features respectively. However, the training patterns and many parameters are designed empirically and set manually in Fukushima's Neocognitron. In this paper, we use Genetic Algorithms (GAS) to tune the parameters of Neocognitron and search its reasonable training pattern sets. First of all, the correlation amongst the training patterns is considered as a critical factor affecting Neocognitron's performance, but it is ignored in the design of the original Neocognitron. And then, a GA-based supervised learning of the Neocognitron is proposed to tune the parameters and search training patterns. The results prove that the performance of a Neocognition is sensitive to its training patterns, selectivity and receptive fields, and can be improved by this supervised learning on the basis of GAS and the correlation analysis.

show abstract

Section: Introductionmentioning

confidence: 99%

GA-based supervised learning of Neocognitron

Shi

Tan²

2000

Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challeng

View full text Add to dashboard Cite

show abstract

“…13 The whole network architecture of the Neocognitron is built from setting zero planes in each layer at the beginning. The size adaptation of the network for a given application helps users reduce the effort in parameter adjustment.…”

Section: Introductionmentioning

confidence: 99%

Neocognitron's Parameter Tuning by Genetic Algorithms

Shi

Dong

Yeung

1999

Int. J. Neur. Syst.

View full text Add to dashboard Cite

The further study on the sensitivity analysis of Neocognitron is discussed in this paper. Fukushima's Neocognitron is capable of recognizing distorted patterns as well as tolerating positional shift. Supervised learning of the Neocognitron is fulfilled by training patterns layer by layer. However, many parameters, such as selectivity and receptive fields are set manually. Furthermore, in Fukushima's original Neocognitron, all the training patterns are designed empirically. In this paper, we use Genetic Algorithms (GAs) to tune the parameters of Neocognitron and search its reasonable training pattern sets. Four contributions are claimed: first, by analyzing the learning mechanism of Fukushima's original Neocognitron, the correlations amongst the training patterns are claimed to affect the performance of Neocognitron, tuning the Neocognitron's number of planes is equivalent to searching reasonable training patterns for its supervised learning; second, a GA-based supervised learning of the Neocognitron is carried out in this way, searching the parameters and training patterns by GAs but specifying the connection weights by training the Neocognitron; third, other than traditional GAs which are unsuitable for the large searching space of training patterns set, the cooperative coevolution is incorporated to play this role; fourth, an effective fitness function is given out when applying the above methodology into numeral recognition. The evolutionary computation in our initial experiments is implemented based on the original training pattern set, e.g. the individuals of the population are generated from Fukushima's original training patterns during initialization of GAs. The results prove that our correlation analysis is reasonable, and show that the performance of a Neocognitron is sensitive to its training patterns, selectivity and receptive fields, especially, the performance is not monotonically increasing with respect to the number of training patterns, and this GA-based supervised learning is able to improve Neocognitron's performance.

show abstract

“…The tuning of the network can be complicated because of the large number of parameters. Recently it has been shown that the model can be greatly simplified while preserving its interesting properties of self-organization and tolerance of image deformations (Trotin et al 1991). The neocognitron can be used for various practical applications (e.g., Fukushima 1988;Fukushima and Imagawa 1993).…”

Section: Introductionmentioning

confidence: 99%

Pattern recognition in the neocognitron is improved by neuronal adaptation

Ooyen

Nienhuis

1993

Biol. Cybern.

View full text Add to dashboard Cite

We demonstrate that equipping the neurons of Fukushima's neocognitron with the phenomenon that a neuron decreases its activity when repeatedly stimulated (adaptation) markedly improves the pattern discriminatory power of the network. By means of adaptation, circuits for extracting discriminating features develop preferentially. In the original neocognitron, in contrast, features shared by different patterns are preferentially learned, as connections required for extracting them are more frequently reinforced.

show abstract

Acquired Structure, Adapted Parameters: Modifications of the Neocognitron

Cited by 5 publications

References 3 publications

GA-based supervised learning of Neocognitron

GA-based supervised learning of Neocognitron

Neocognitron's Parameter Tuning by Genetic Algorithms

Pattern recognition in the neocognitron is improved by neuronal adaptation

Contact Info

Product

Resources

About