{"id":71,"date":"2011-07-24T14:54:35","date_gmt":"2011-07-24T18:54:35","guid":{"rendered":"http:\/\/blogs.bu.edu\/suchi\/?page_id=71"},"modified":"2026-02-18T18:35:30","modified_gmt":"2026-02-18T23:35:30","slug":"neural-networks","status":"publish","type":"page","link":"https:\/\/blogs.bu.edu\/suchi\/neural-networks\/","title":{"rendered":"AI\/ ML &#8211; Pattern Recognition and Classification"},"content":{"rendered":"<p>My early work used early AI Neural networks are learning algorithms\u00a0 for pattern classification, estimation and modeling complex relationships between inputs and outputs. In my early work, I have used a variety of neural networks including backpropagation, ART (Adaptive Resonance Theory) models, and SOM (Self-organizing Maps) for landcover classification, change detection, estimation and other problems.<\/p>\n<p>The map below shows ARTMAP classification of vegetation in the Sierras using Landsat data<\/p>\n<p><a href=\"http:\/\/blogs.bu.edu\/suchi\/files\/2011\/07\/ARTMAP-Vegetation-Mapping2.jpg\"><img loading=\"lazy\" class=\"aligncenter size-full wp-image-130\" src=\"http:\/\/blogs.bu.edu\/suchi\/files\/2011\/07\/ARTMAP-Vegetation-Mapping2.jpg\" alt=\"ARTMAP Vegetation Mapping\" width=\"492\" height=\"625\" srcset=\"https:\/\/blogs.bu.edu\/suchi\/files\/2011\/07\/ARTMAP-Vegetation-Mapping2.jpg 492w, https:\/\/blogs.bu.edu\/suchi\/files\/2011\/07\/ARTMAP-Vegetation-Mapping2-236x300.jpg 236w\" sizes=\"(max-width: 492px) 85vw, 492px\" \/><\/a><\/p>\n<p><a href=\"http:\/\/blogs.bu.edu\/suchi\/files\/2011\/07\/N.America_NN_DT.jpg\"><img loading=\"lazy\" class=\"aligncenter size-full wp-image-128\" src=\"http:\/\/blogs.bu.edu\/suchi\/files\/2011\/07\/N.America_NN_DT.jpg\" alt=\"N.America_NN_DT\" width=\"303\" height=\"391\" srcset=\"https:\/\/blogs.bu.edu\/suchi\/files\/2011\/07\/N.America_NN_DT.jpg 303w, https:\/\/blogs.bu.edu\/suchi\/files\/2011\/07\/N.America_NN_DT-232x300.jpg 232w\" sizes=\"(max-width: 303px) 85vw, 303px\" \/><\/a><\/p>\n<p>The second map shows the classification differences between ARTMAP and Decision Tree classification of landcover in N. America using MODIS. Darkest areas show the highest differentiation between two classifiers while green areas represent agreement.<\/p>\n<p>Collaborators: <a href=\"http:\/\/techlab.bu.edu\/members\/gail\/\">Gail Carpenter<\/a> (CNS Tech Lab), Curtis Woodcock and Alan Strahler (Boston University).<\/p>\n<p>See <span style=\"text-decoration: underline\">some<\/span> of our papers:<br \/>\n1. Carpenter et al. <a href=\"http:\/\/techlab.bu.edu\/members\/gail\/articles\/127_Mixtures_RSE_1999_.pdf\">Mixture Modeling<\/a><br \/>\n2. Carpenter, Gopal, Woodcock. <a href=\"http:\/\/techlab.bu.edu\/members\/gail\/articles\/128_RSE_Sierra_1999.pdf\">Vegetation Mapping<\/a><\/p>\n<p>3.\u00a0Abuelgasim, A., Ross, W. D., Gopal, S., and Woodcock, C. E. (1999). Change detection using\u00a0adaptive neural networks: Environmental damage assessment after the Gulf War, <span style=\"text-decoration: underline\">Remote Sensing\u00a0of the Environment<\/span>, 70 (2), 208-223.<\/p>\n<p>4. Carpenter, G., Gjaja, M., Gopal, S., and Woodcock, C. \u00a0(1997). ART networks in Remote\u00a0Sensing, <span style=\"text-decoration: underline\">IEEE Transactions on Geoscience and Remote Sensing<\/span>, 35(2), 308-325.<\/p>\n<p>5.\u00a0Liu, W., Gopal, S., and Woodcock, C. \u00a0(2001). Spatial data mining for classification, visualization\u00a0and interpretation with ARTMAP neural networks, in Robert L. Grossman (Editor), et al <span style=\"text-decoration: underline\">Data\u00a0mining for scientific and engineering applications<\/span>, Kluwer Academic Publishers, Netherlands.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>My early work used early AI Neural networks are learning algorithms\u00a0 for pattern classification, estimation and modeling complex relationships between inputs and outputs. In my early work, I have used a variety of neural networks including backpropagation, ART (Adaptive Resonance Theory) models, and SOM (Self-organizing Maps) for landcover classification, change detection, estimation and other problems. &hellip; <a href=\"https:\/\/blogs.bu.edu\/suchi\/neural-networks\/\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;AI\/ ML &#8211; Pattern Recognition and Classification&#8221;<\/span><\/a><\/p>\n","protected":false},"author":2207,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"open","ping_status":"open","template":"","meta":[],"_links":{"self":[{"href":"https:\/\/blogs.bu.edu\/suchi\/wp-json\/wp\/v2\/pages\/71"}],"collection":[{"href":"https:\/\/blogs.bu.edu\/suchi\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/blogs.bu.edu\/suchi\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/blogs.bu.edu\/suchi\/wp-json\/wp\/v2\/users\/2207"}],"replies":[{"embeddable":true,"href":"https:\/\/blogs.bu.edu\/suchi\/wp-json\/wp\/v2\/comments?post=71"}],"version-history":[{"count":24,"href":"https:\/\/blogs.bu.edu\/suchi\/wp-json\/wp\/v2\/pages\/71\/revisions"}],"predecessor-version":[{"id":340,"href":"https:\/\/blogs.bu.edu\/suchi\/wp-json\/wp\/v2\/pages\/71\/revisions\/340"}],"wp:attachment":[{"href":"https:\/\/blogs.bu.edu\/suchi\/wp-json\/wp\/v2\/media?parent=71"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}