{"id":599,"date":"2022-03-14T18:44:28","date_gmt":"2022-03-14T18:44:28","guid":{"rendered":"http:\/\/new.patterncomputer.com\/?p=599"},"modified":"2022-04-08T22:16:25","modified_gmt":"2022-04-08T22:16:25","slug":"pattern-computer-reveals-groundbreaking-new-technology-for-explainable-ai-at-the-fire22-conference","status":"publish","type":"post","link":"http:\/\/new.patterncomputer.com\/pattern-computer-reveals-groundbreaking-new-technology-for-explainable-ai-at-the-fire22-conference\/","title":{"rendered":"Pattern Computer Reveals Groundbreaking New Technology for Explainable AI at the FiRe22 Conference"},"content":{"rendered":"
REDMOND, WA, MARCH 14, 2022 \u2013 In a major reveal at the Future In Review event last week, Pattern Computer\u00ae<\/sup>, Inc. (PCI) disclosed that it has made a major breakthrough in explainable AI (XAI). Pattern Computer\u2019s proprietary Pattern Discovery Engine\u2122 can derive previously hidden local manifolds from neural net models (including deep neural nets).<\/p>\n While methods for a partial picture of what deep neural networks learn have been around for years1<\/sup> they don\u2019t actually reveal how the neural network made its decision\u2014the other methods only illustrate which features may have been involved in the neural network making a decision.<\/p>\n According to Dr. J. Ben Brown, Computational Biologist and Staff Scientist in Environmental Genomics and Systems Biology at Lawrence Berkely National Lab, \u201cThe major advance here for PCI is that we now actually see \u2013 through the eyes of the neural network \u2013 precisely the decision function it has learned. That\u2019s a sea change.”<\/em><\/p>\n Referring at FiRe 22 to PCI\u2019s solving the \u201cblack box\u201d problem shared by all neural nets, Brown noted \u201cThat\u2019s what Pattern Computer has been able to do \u2013 to turn any deep learning AI algorithm into a \u2018glass box.\u2019 XAI has the potential to be as impactful as the arrival of calculus. We are coming to an inflection point, and that is XAI, and that is Pattern Computer. This is completely new and novel. Nothing that is out there today is explainable AI.”<\/em><\/p>\n Pattern Computer\u2019s breakthrough enables many scientific approaches, and will impact society in interesting ways. Mark Anderson, Pattern Computer\u2019s CEO, points out, \u201cThere is significant direct interest in the application of our breakthroughs to the EU\u2019s GDPR law, which requires firms to explain to their customers how their AI-mediated decisions were decided. This law has been unenforceable until today, because it has not been possible to understand or explain how deep neural networks make decisions. Now, we can: Pattern Computer\u2019s new XAI system can extract the actual decision functions from neural networks, and those decisions can be explained and studied.”<\/em><\/p>\n About Pattern Computer<\/strong><\/p>\n Pattern Computer, Inc. uses its proprietary Pattern Discovery Engine™<\/sup> to solve the most important and intractable problems in business and medicine. Its proprietary mathematical techniques can find complex patterns in very-high-order data that have eluded detection by others.<\/p>\n While the company is currently applying its computational platform to the challenging field of drug discovery, it is also making Pattern Discoveries for partners in other sectors, including additional biomedical research, materials science, aerospace manufacturing, veterinary medicine, air traffic operations, resource extraction and finance.<\/p>\n