DIFFERENT WAYS TO SUPPORT INTELLIGENT ASSISTANT SYSTEMS BY USE OF MACHINE LEARNING-METHODS

Intelligent assistant systems provide an adequate organization of huma n-computer interaction for complex problem solving. These knowledge-ba sed systems are characterized by a cooperative problem-solving procedu re. User and system cooperate intensively to produce the aimed result. Machine learning methods can provide significant support for assistan t systems. In this article, it is pointed out how assistant systems ca n be supported in various ways. For instance, machine learning methods can extend, revise, optimize, and adapt the knowledge base of an assi stant system. In this way, they can contribute to the utility and main tainability of an intelligent assistant system. They can also increase the flexibility and effectiveness of human-computer interaction. The learning apprentice system COSIMA is presented which acquires knowledg e about single problem-solving steps from observation of the user. Pro duction rules for floorplanning, a sub-task of VLSI design, are acquir ed and refined cooperatively by different learning strategies.