?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.title=Hopfield+Networks+in+Relevance+and+Redundancy+Feature+Selection+Applied+to+Classification+of+Biomedical+High-Resolution+Micro-CT+Images&rft.creator=Auffarth%2C+B.&rft.creator=Lopez%2C+M.&rft.creator=Cerquides%2C+J.&rft.subject=Machine+Learning&rft.subject=Statistical+Models&rft.description=We+study+filter%E2%80%93based+feature+selection+methods+for+classification+of+biomedical+images.+For+feature+selection%2C+we+use+two+filters+%E2%80%94+a+relevance+filter+which+measures+usefulness+of+individual+features+for+target+prediction%2C+and+a+redundancy+filter%2C+which+measures+similarity+between+features.+As+selection+method+that+combines+relevance+and+redundancy+we+try+out+a+Hopfield+network.+We+experimentally+compare+selection+methods%2C+running+unitary+redundancy+and+relevance+filters%2C+against+a+greedy+algorithm+with+redundancy+thresholds+%5B9%5D%2C+the+min-redundancy+max-relevance+integration+%5B8%2C23%2C36%5D%2C+and+our+Hopfield+network+selection.+We+conclude+that+on+the+whole%2C+Hopfield+selection+was+one+of+the+most+successful+methods%2C+outperforming+min-redundancy+max-relevance+when%0D%0Amore+features+are+selected.+&rft.publisher=Springer+Heidelberg&rft.contributor=Perner%2C+Petra&rft.date=2008-07-17&rft.type=Book+Chapter&rft.type=PeerReviewed&rft.format=application%2Fpdf&rft.identifier=http%3A%2F%2Fcogprints.org%2F7061%2F1%2Fleipzip08.pdf&rft.identifier=++Auffarth%2C+B.+and+Lopez%2C+M.+and+Cerquides%2C+J.++(2008)+Hopfield+Networks+in+Relevance+and+Redundancy+Feature+Selection+Applied+to+Classification+of+Biomedical+High-Resolution+Micro-CT+Images.++%5BBook+Chapter%5D+++++&rft.relation=http%3A%2F%2Fcogprints.org%2F7061%2F