All of a sudden comes a spate of books glorifying neural networks. Do we sense a paradigm shift here? Down with the old reductionist approach of artificial intelligence? Up with the biologically more relevant parallel processing network models? So it would seem, but don't expect consensus. Unlike other recent writers in the field who argue for a specific theory (e.g., Gerald M. Edelman in Bright Air, Brilliant Fire, p. 297), Jubak (former editor of Venture magazine) provides a broad survey of current work in academia and industry, leaving it up to the reader to judge. Jubak is an enthusiast who's on top of developments in speech and pattern perception, robotics, organizing principles in brain development, and so on—but it's just not easy to convey the structure and behavior of computer networks in which the builders themselves are uncertain about what happens in the ``hidden'' layers connected to an input layer (responding to light signals, for example) and to the output layer (identifying a letter or other pattern). Overall, the models try to emulate features of the human brain in its connectivity and its ability to learn. ``Learning'' is often defined in terms of the Hebb synapse—a strengthening of the connection between neurons that fire together. Some basis for the Hebb synapse is revealed late in the book in the discovery of the NMDA receptor—one of two kinds of receptors at neuronal synapses that may be responsible for long-term potentiation. At this microcosmic level of brain science, we learn, the nerve cell itself may be a master microprocessor computing its behavior from multiple inputs summed over time and space and subject to its own feedback circuits. Jubak's useful if demanding survey reveals that the state of the science is such that the more we know the less we know; but that what the brain does is absolutely thrilling—and beautiful. (Line drawings throughout.)
Pub Date: May 22, 1992
ISBN: 0-316-47555-6
Page Count: 368
Publisher: Little, Brown
Review Posted Online: May 19, 2010
Kirkus Reviews Issue: April 1, 1992
BOOK REVIEW
Stricter than, say, Bergen Evans or W3 ("disinterested" means impartial — period), Strunk is in the last analysis...
Privately published by Strunk of Cornell in 1918 and revised by his student E. B. White in 1959, that "little book" is back again with more White updatings.
Stricter than, say, Bergen Evans or W3 ("disinterested" means impartial — period), Strunk is in the last analysis (whoops — "A bankrupt expression") a unique guide (which means "without like or equal").Pub Date: May 15, 1972
ISBN: 0205632645
Page Count: 105
Publisher: Macmillan
Review Posted Online: Oct. 28, 2011
Kirkus Reviews Issue: May 1, 1972
This is not the Nutcracker sweet, as passed on by Tchaikovsky and Marius Petipa. No, this is the original Hoffmann tale of 1816, in which the froth of Christmas revelry occasionally parts to let the dark underside of childhood fantasies and fears peek through. The boundaries between dream and reality fade, just as Godfather Drosselmeier, the Nutcracker's creator, is seen as alternately sinister and jolly. And Italian artist Roberto Innocenti gives an errily realistic air to Marie's dreams, in richly detailed illustrations touched by a mysterious light. A beautiful version of this classic tale, which will captivate adults and children alike. (Nutcracker; $35.00; Oct. 28, 1996; 136 pp.; 0-15-100227-4)
Pub Date: Oct. 28, 1996
ISBN: 0-15-100227-4
Page Count: 136
Publisher: Harcourt
Review Posted Online: May 19, 2010
Kirkus Reviews Issue: Aug. 15, 1996
BOOK REVIEW
BOOK REVIEW
© Copyright 2025 Kirkus Media LLC. All Rights Reserved.
Follow
Popular in this Genre
We can’t wait for you to join Kirkus!
It’s free and takes less than 10 seconds!
Already have an account? Log in.
OR
Sign in with GoogleTrouble signing in? Retrieve credentials.
Welcome Back!
OR
Sign in with GoogleTrouble signing in? Retrieve credentials.
