Artificial Intelligence Project 1 Neural Networks Biointelligence Lab School of Computer Sci. & Eng. Seoul National University
(C) SNU CSE BioIntelligence Lab 2 Outline Classification Problems Task 1 Estimate several statistics on Diabetes data set Task 2 Given unknown data set, find the performance as good as you can get The test data is hidden.
(C) SNU CSE BioIntelligence Lab 3 Network Structure (1) … positive negative f pos (x) > f neg (x),→ x is postive
(C) SNU CSE BioIntelligence Lab 4 Network Structure (2) … f (x) > thres,→ x is postive
Medical Diagnosis: Diabetes
(C) SNU CSE BioIntelligence Lab 6 Pima Indian Diabetes Data (768) 8 Attributes Number of times pregnant Plasma glucose concentration in an oral glucose tolerance test Diastolic blood pressure (mm/Hg) Triceps skin fold thickness (mm) 2-hour serum insulin (mu U/ml) Body mass index (kg/m 2 ) Diabetes pedigree function Age (year) Positive: 500, negative: 268
(C) SNU CSE BioIntelligence Lab 7 Report (1/4) Number of Epochs
(C) SNU CSE BioIntelligence Lab 8 Report (2/4) Number of Hidden Units At least, 10 runs for each setting # Hidden Units TrainTest Average SD BestWorst Average SD BestWorst Setting 1 Setting 2 Setting 3
(C) SNU CSE BioIntelligence Lab 9 Report (3/4)
(C) SNU CSE BioIntelligence Lab 10 Report (4/4) Normalization method you applied. Other parameters setting Learning rates Threshold value with which you predict an example as positive. If f(x) > thres, you can say it is positive, otherwise negative.
(C) SNU CSE BioIntelligence Lab 11 Challenge (1) Unknown Data Data for you: 3282 examples 16 dim-input vector labeled one of 5 classes 5 classes are: A,B, C, D, E Test data 582 examples Labels are HIDDEN!
(C) SNU CSE BioIntelligence Lab 12 Challenge (2) Data Train.txt : 3282 x 17 (16987 examples, 16 dim-input + with last column as label) Test.txt: 582 x 16 (582 examples, 16 dim-input, labels are hidden) Verify your NN at
(C) SNU CSE BioIntelligence Lab 13
(C) SNU CSE BioIntelligence Lab 14 A B C D E
(C) SNU CSE BioIntelligence Lab 15
(C) SNU CSE BioIntelligence Lab 16 제출할 것 최고 성능을 낸 제출자 명시 뉴럴넷 구조 최고 성능을 이끌어 내기 위해 자신이 시도한 내역 기술 자신의 최고 성능 (score) : 성능과 점수는 상관 관계가 작습니다.
(C) SNU CSE BioIntelligence Lab 17 References Source Codes Free softwares NN libraries (C, C++, JAVA, …) MATLAB Tool box Weka Web sites
(C) SNU CSE BioIntelligence Lab 18 Pay Attention! Due (October 14, 2003): until pm 11:59 Submission Results obtained from your experiments Compress the data Via Report: Hardcopy!! Used software and running environments Results for many experiments with various parameter settings Analysis and explanation about the results in your own way
(C) SNU CSE BioIntelligence Lab 19 Optional Experiments Various learning rate Number of hidden layers Different k values Output encoding