https://www.wikiworld.com/index.php?action=history&feed=atom&title=DeepBlue 2026-05-06T15:32:52Z Revision history for this page on the wiki MediaWiki 1.45.1 https://www.wikiworld.com/index.php?title=DeepBlue&diff=1632&oldid=prev 2026-01-28T11:54:25Z

<p>Imported current content</p> <p><b>New page</b></p><div>A highly parallel computer developed by [[IBM]] to play chess.<br /> <br /> (See [[KasparovVsDeeperBlue]] ISBN:0713483229)<br /> <br /> It uses essentially a brute force algorithm.<br /> <br /> It produces moves as good or better than a grand master.<br /> <br /> An interesting challenge is how to extend that power to make explanations for its choices of moves that are intelligible to a human. How does one post process such a deep-tree analysis into a summary that is concise and understandable, the way first class chess game annotations do?<br /> <br /> * Nice expert system. But it doesn&#039;t learn, does it?<br /> <br /> * Chess Analysis just tell you why that move is good. It doesn&#039;t mean that it is focused on winning necessarily. Just a Communal Acquired Knowledge, isn&#039;t it? You could attach a general comment to that line of code/tree choice. That would then make it the same thing then, wouldn&#039;t it? --[[StarPilot]]</div>

imported>Import