Algorithms, Data, and Hypotheses: Learning in Open Worlds

This paper contains an informal discussion about how t o s y n thesize reasonable hypotheses from data. This is a fundamental problem for any s y-stem acting in the real world. The problem consists of three interconnected subproblems: tting the past data to a hypothesis (model), selecting promising new data in order to increase the validity of the hypothesis, and selecting a hypothesis in a class of hypotheses (models). We argue that molecular electronics may be important for the development o f s u c h systems. First, it provides the computing power needed for such systems. Second, it can help in deening a new computational model urgently needed for the design of an artiicial systems synthesizing hypotheses about processes of the real world.