**7. Learning and recognition**

The selection of the ANN for this purpose was based on previous results where the convergence time for some ANN architectures was evaluated during recognition tasks of simple geometrical parts. The assessed networks were Backpropagation, Perceptron and Fuzzy ARTMAP using the BOF vector. Results showed that the FuzzyARTMAP network outperformed the other networks with lower training/testing times (0.838ms/0.0722ms) compared with Perceptron (5.78ms/0.159 ms) and Backpropagation (367.577ms/0.217 ms) (Lopez-Juarez, et al., 2010).

In the Fuzzy ARTMAP (FAM) network there are two modules ARTa and ARTb and an inter-ART module "Map-field" that controls the learning of an associative map from ARTa recognition categories to ARTb categories (Carpenter and Grossberg, 1992). This is illustrated in Figure 8.

The Map-field module also controls the match tracking of ARTa vigilance parameter. A mismatch between Map field and ARTa category activated by input Ia and ARTb category activated by input Ib increases ARTa vigilance by the minimum amount needed for the system to search for, and if necessary, learn a new ARTa category whose prediction matches the ARTb category. The search initiated by the inter-ART reset can shift attention to a novel cluster of features that can be incorporated through learning into a new ARTa recognition category, which can then be linked to a new ART prediction via associative learning at the Map-field.

A vigilance parameter measures the difference allowed between the input data and stored patterns. Therefore, this parameter affects the selectivity or granularity of the network prediction. For learning, the FuzzyARTMAP has 4 important factors: Vigilance in the input module (a), vigilance in the output module (b), vigilance in the Map field (ab) and learning rate ().

Fig. 8. FuzzyARTMAP Architecture

For the specific case of the work presented in this article, the input information is concatenated and presented as a sole input vector A, while the vector B receives the correspondence associated to the respective component, during the training process.
