抄録
In this paper we propose an algorithm for learning from positive examples only, based on a modified cognitive control model. This problem arises when positive examples are readily available while negative examples are difficult or impossible to obtain. In particular, we are motivated by an application of the proposed algorithm to learning strategies from real-life optimisation problem solutions provided by skilled humans. Using a packing problem as an example, we performed an experiment in which the performance of the proposed algorithm was compared to that of one-class Support Vector Machines and auto-encoding neural network algorithms. The results of the experiment show that the proposed algorithm compares favourably to the other two algorithms.
