Combining symbolic and neural learning

The last ten or so years have produced an explosion in the amount of research on machine learning. This rapid growth has occurred, largely independently, in both the symbolic and connectionist (neural network) machine learning communities. Fortunately, over the last few years these two communities have become less separate, and there has been an increasing amount of research that can be considered a hybrid of the two approaches. This extended abstract reviews some of the research that combines the symbolic and neural network approaches to artificial intelligence.