Abstract | ||
---|---|---|
Visual learning is an important aspect of fly life. Flies are able to extract visual cues from objects, like colors, vertical and horizontal distributedness, and others, that can be used for learning to associate a meaning to specific features (i.e. a reward or a punishment). Interesting biological experiments show trained stationary flying flies avoiding flying towards specific visual objects, appearing on the surrounding environment. A decision making process has been identified in the flies that had been trained to avoid objects with specific visual features. In presence of a feature the fly has to decide which features are the most relevant to make a choice. The decision making strategy is guided by a pre-wired hierarchical categorization of the features that, for instance, leads the fly to give more importance to color with respect to shape. A bio-inspired architecture has been proposed to model the fly behavior and experiments on roving robots were performed. Statistical comparisons have been considered and mutant-like effect on the model has been also investigated. |
Year | DOI | Venue |
---|---|---|
2011 | 10.3233/978-1-60750-972-1-284 | FRONTIERS IN ARTIFICIAL INTELLIGENCE AND APPLICATIONS |
Keywords | Field | DocType |
hybrid robot,visual cue-based navigation,spiking neurons,Drosophila melanogaster | Computer science,Artificial intelligence,Machine learning | Conference |
Volume | ISSN | Citations |
234 | 0922-6389 | 1 |
PageRank | References | Authors |
0.38 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Paolo Arena | 1 | 261 | 47.43 |
Luca Patané | 2 | 104 | 17.31 |
Pietro Savio Termini | 3 | 8 | 1.60 |