We consider multitask learning of visual concepts within genetic programming (GP) framework. The proposed method evolves a population of GP individuals, with each of them composed of several GP trees that process visual primitives derived from input images. The two main trees are delegated to solving two different visual tasks and are allowed to share knowledge with each other by calling the remaining GP trees (subfunctions) included in the same individual. The method is applied to the visual learning task of recognizing simple shapes, using generative approach based on visual primitives, introduced in [17]. We compare this approach to a reference method devoid of knowledge sharing, and conclude that in the worst case cross-task learning performs equally well, and in many cases it leads to significant performance improvements in one or both solved tasks.

Abstract. We propose a learning algorithm that reuses knowledge acquired in past learning sessions to improve its performance on a new learning task. The method concerns visual learning and uses genetic programming to represent hypotheses, each of them being a procedure that processes visual primitives derived from the training images. The process of recognition is generative, i.e., a procedure is supposed to restore the shape of the processed object by drawing its reproduction on a separate canvas. This basic method is extended with a knowledge reuse mechanism that allows learners to import genetic material from hypotheses that evolved for the other decision classes (object classes). We compare both methods on a task of handwritten character recognition, and conclude that knowledge reuse leads to signi cant improvement of classi cation accuracy and reduces the risk of over tting. 1

We propose a method of knowledge reuse between evolutionary processes that solve different optimization tasks. We define the method in the framework of tree-based genetic programming (GP) and implement it as code reuse between GP trees that evolve in parallel in separate populations delegated to particular tasks. The technical means of code reuse is a crossbreeding operator which works very similar to standard tree-swapping crossover. We consider two variants of this operator, which differ in the way they handle the incompatibility of terminals between the considered problems. In the experimental part we demonstrate that such code reuse is usually beneficial and leads to success rate improvements when solving the common boolean benchmarks.