Principles of Neurodynamics. Perceptrons and the Theory of Brain Mechanisms.

In recent years, there have been a number of engineering projects concerned with the design of brain models for pattern recognition and artificial intelligence. The basic assumption, underlying these projects is that the brain operates by built-in algorithmic methods similar to those employed in modern digital computers. Hence, nervous activity can be simulated by these computers. The value of such a program has been challenged by Lashley and others on the grounds that computer-simulated behavior is artificial, that the model is an invention operating on extrabiological principles. In this formidable book, Rosenblatt has offered a somewhat different program involving the design and testing of brain models described as perceptrons. His program is concerned not with devices for artificial intelligence, but, rather, with "the physical structures and neurodynamics principles which underly "natural intelligence." A perceptron consists of a set of signal generating units ("neuro-mimes") connected together to form a network.