A graph-based model of object recognition self-learning
Anna Gorbenko · Advanced Studies in Theoretical Physics · 2013
In this paper, we study the object recognition self-learning for robots. In particular, we consider the self-learning during solution of typical tasks. We propose a graph-based model for self-learning. This model is based on the problem of monochromatic path for given set of weights. We prove that the problem is NP-complete. We consider an approach to solve the problem. This approach is based on an explicit reduction from the problem to the satisfiability problem.