See Mitchell's recent text [6] or Goldberg's classic text [4] for good introductions to Genetic algorithms. Evolutionary programming can be more easily covered in a few lectures than neural networks. Each of the following topics could span an entire lecture or be briefly mentioned in a more general overview. The first topic provides an introduction to the algorithm and its connection to the theory of natural selection. The second topic could be skipped if only a quick survey was desired, but is important in understanding how and why genetic algorithms are successful. The third topic could span more than one lecture since there are numerous interesting applications of GAs (especially in combining the local learning of neural networks with the global learning of GAs). The fourth topic ties in well with the more traditional AI topic of production systems. Classifier systems are essentially production systems with a learning component. The final topic covers a fast growing subarea of genetic algorithms called genetic programming. Rather than evolving bit strings, in genetic programming, fragments of code are combined to evolve programs.