AN EVALUATION OF RECENT DEVELOPMENTS IN THE FIELD OF LEARNING MACHINES - Oliver G. Selfridge Lincoln Laboratory*, Massachusetts Institute of Technology

When it was suggested that I contribute a paper to this session, I had in mind that I would discuss and try and put into some kind of technological context the other papers of the session. Much of my own work of recent years has been in the field of learning machines, and artificial intelligence. There are some of us who are interested in seeing machines behave intelligently, and some of us who are only interested in having the machine simulate theories about how real brains work. I suppose that the former must predominate here, and I belong to that class myself. It is therefore a reasonable question to ask how we shall recognize intelligent behavior in a machine when we manage to find some. I'm not sure that I can answer that except by saying that I should try to use the same standards that I use in people; but I start out by being prejudiced that people, my friends at least, are intelligent and that machines are not, even the ones I'm friendly to. There are a very few computer programs that have behavior which, even if not bright, cannot be called stupid; the famous checkers program by Arthur Samuel of IBM is one.