پديد آورنده :
اشراقي جزي، سميرا
عنوان :
يادگيري چند نمونه اي با استفاده از برنامه ريزي درجه دو و اتوماتاي يادگير سلولي
مقطع تحصيلي :
كارشناسي ارشد
گرايش تحصيلي :
هوش مصنوعي
محل تحصيل :
اصفهان: دانشگاه صنعتي اصفهان، دانشكده برق و كامپيوتر
صفحه شمار :
هشت،57ص.: مصور،جدول،نمودار
يادداشت :
ص.ع.به فارسي و انگليسي
توصيفگر ها :
بسته هاي آموزشي
تاريخ نمايه سازي :
3/10/92
استاد داور :
مازيار پالهنگ، مهران صفاياني
دانشكده :
مهندسي برق و كامپيوتر
چكيده فارسي :
به فارسي و انگليسي: قابل رويت در نسخه ديجيتالي
چكيده انگليسي :
Multi Instance Learning by Quadratic Programming and Cellular Learning Automata Samira Eshraghi s eshraghijazi@ec iut ac ir Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan Iran Supervisor Abdolreza Mirzaie Mirzaie@cc iut ac ir Abstract One of the most important machine learning methods is supervised learning in which labled data is used to traine the system But some times determining the label of each individual data sample is difficult and even impossible and only the lable of a set of samples is specified In these situations a kind of leaning called multi instance learning is used which is introduced for working with ambiguous data and the possibility of classification without specifing the class of all data samples In multi instance learning training data are labeled bags that each of them includes several unlabeled instances The task of the learner is to determine the class of new bags Multi instance learning is used in many applications such as prediction of drug activity detecting an object in an image and classification of texts In this thesis two algorithms are proposed solving the multi instance learning problems The first algorithm using the characteristics of multi instance learning problem defines an objective function of degree 2 and then by quadratic prgramming determines the label of unknown instances in such a way that this objective function is optimized The second algorithm uses a probabilistic method called cellular learning automata to determine the label of unknown instances Both algorithms are examined on available data in the field of multi instance learning and they achived acceptable results in comparison with other methods PDF created with pdfFactory trial version www pdffactory com
استاد داور :
مازيار پالهنگ، مهران صفاياني