A constructive induction model using genetic programming is presented. The model evolves new attributes starting from a random population of possible attributes constructed as functions of the original attributes. The model is tested on hard supervised learning problems and its performance is compared with backpropagation and C4.5. The performance of the system on learning incomplete 4-bit parity is reported to be better. 1 INTRODUCTION Constructive induction (CI) is an effort to improve the attribute vector of a learning problem in order to make the problem more easily learned for a particular learning algorithm(see [ 9 ] , [ 11 ] , [ 21 ] ). CI is often used to tackle hard problems for a given learning algorithm L - problems are hard for L if the training set contains all the relevant information for the induction of the target function but this information cannot be extracted by L (see [ 13 ] ). In general, CI is used to deal with problems that are hard for the most used learning ...

In constructive induction (CI), the learner's problem representation is modified as a normal part of the learning process. This is useful when the initial representation is inadequate or inappropriate. In this paper, I argue that the distinction between constructive and non-constructive methods is unclear. I propose a theoretical model which allows (a) a clean distinction to be made and (b) the process of CI to be properly motivated. I also show that although constructive induction has been used almost exclusively in the context of supervised learning, there is no reason why it cannot form a part of an unsupervised regime. 1 Introduction Constructive induction (CI) is of use when the initial representation for a problem obstructs the application of ordinary inductive methods [1]. Wnek and Michalski [2] have divided constructive induction methods into several types including hypothesis-driven (HCI) methods, data-driven (DCI) methods and knowledge-driven (KCI) methods. Practical methods...

In constructive induction (CI), the learner's problem representation is modified as a normal part of the learning process. This may be necessary if the initial representation is inadequate or inappropriate. However, the distinction between constructive and non-constructive methods appears to be highly ambiguous. Several conventional definitions of the process of constructive induction appear to include all conceivable learning processes. In this paper I argue that the process of constructive learning should be identified with that of relational learning (i.e., I suggest that what constructive learners really learn is relationships) and I describe some of the possible benefits that might be obtained as a result of adopting this definition.