In the Image of the Brain: Breaking the Barrier Between the Human Mind and Intelligent Machines

Neural networks are computing devices capable of learning and evolving. Modeled after the neurobiology of the human brain, with immense numbers of processors, they are either simulated in computer programs or actually built out of silicon. These ``brain-like'' gizmos can identify a person's gender from a facial image, assess mortgage risks or locate an animal from the sound it makes. In a solid, valuable report, former Venture magazine editor Jubak takes readers to the cutting edge of this field by interviewing neural network researchers at their drawing-boards. Among them are University of Colorado's Micahael Mozer, inventor of a ``Bach machine'' that composes music; Stanford neuroscientist Eric Knudsen, who studies barn owls to learn how brains map spatial patterns; and Charles Gray, a researcher in Frankfurt, Germany, who believes he may have found consciousness itself in the oscillations of brain neurons firing in synchronization. In the end, though, the mind seems as elusive as ever. (June)