数据挖掘2-.doc

Part I: 书面作业： 1. Compute the Information Gain for Gender, Car Type and Shirt Size. Construct a decision tree with Information Gain. Design a multilayer feed-forward neural network (one hidden layer) for the given data. Label the nodes in the input and output layers. Using the neural network obtained above, show the weight values after one iteration of the backpropagation algorithm, given the training instance “(M, Family, Small). Indicate your initial weight values and biases and the learning rate used. (a) (b) (c) 注： F M Family Sports Luxury Small Medium Large Ex Large （d）学习率，C0: 1，C1：1 “(M, Family, Small)的类为C0，则 初始输入、权重、偏倚值 0 1 1 0 0 1 0 0 0 0.2 0.1 0.1 -0.2 -0.2 -0.4 -0.3 0.2 0.3 0.2 0.4 0.1 -0.3 -0.2 -0.2 0.5 0.4 -0.3 -0.4 0.2 -0.4 0.2 0.1 净输入和输出的计算表 单元 净输入 输出 10 11 12 计算每个节点的误差表 单元 12 11 10 计算权重与偏倚的更新 2. Suppose the fraction of undergraduate students who smoke is 15% and the fraction of graduate students who smoke is 23%. If one-?fth of the college students are graduate students and the rest are undergraduates, what is the probability that a student who smokes is a graduate student? Given the information in part (a), is a randomly chosen college student more likely to be a graduate or undergraduate student? Suppose 30% of the graduate students live in a dorm but only 10% of the undergraduate students live in a dorm. If a student smokes and lives in the dorm, is he or she more likely to be a graduate or undergraduate student? You can assume independence between students who live in a dorm and those who smoke. (a)let A：undergraduate student；Bgraduate students；C：smoke P(C|A)=0.15；P(C|B)=0.23；P(B)=0.2；P(A)=0.8；findP(B|C) (b) From ,we can deserve that a randomly chosen college student is more likely to be a undergraduate student. (c) let D: live in the dorm，P(D|B)=0.3，P(D|A)=0.1 so if a student smokes and lives in the dorm,