This book is intended to be an intellectual journey into the domain of human and machine intelligence. The subject matter has been approached from a conceptual and sometimes even philosophical point of view, one biased by our experience in that branch of computer and cognitive science called artificial intelligence (AI). On this
journey we will often be dealing with topics,such as the operation of the brain, where knowledge is lacking, and where there are only vague conjectures as to possible mechanisms. In our review of machine intelligence, we will discuss both the present-day and ultimate limits of machine performance. We intend the book to provide the Scientific American level reader with an understanding of the concept of intelligence, the nature of the cognitive and perceptual capabilities of people and machines, and the representations and algorithms used to attain intelligent behavior. While we have attempted to make the material understandable by an educated layman, we are equally concerned with having something important to say to our professional colleagues and peers. "Boxes" have been used to augment the text. These boxes,and longer appendices, present material of interest that expand on the topics being discussed, and sometimes they may contain technical material of more interest to the specialist. It is intended that the text should stand on its own; the reader can usually omit the boxes until a later
reading. A unifying theme in our exposition is the critically important concept of representation. Issues related to this and other important concepts may be raised in an earlier chapter, our position stated, and then elaborated and supported in later chapters... Our primary purpose in the first part of this book is to provide a basis for understanding the nature of intelligence and intelligent behavior: (a) as it exists in man and higher animals, (b) as it could exist in a machine, and (c) as a scientific discipline concerned with the mechanisms and limits involved in acquiring, representing, and applyingknowledge.The last part of the book deals with perception and primarily vision, the means by which knowledge about our physical environment is acquired. We will see that perceptual behavior, far from being passive or mechanical, requires a reasoning ability at least equal to that needed for the most difficult problem-solving tasks.The flavor of this book can be gleaned from the following brief description of chapter topics.