Lecture 3 Regression Analysis and Classification Dr.李晓瑜Xiaoyu Li Email:xiaoyuuestc@uestc.edu.cn http://blog.sciencenet.cn/u/uestc2014xiaoyu 2019-Spring SunData Group http://www.sundatagroup.org School of Information and Software Engineering,UESTC 1966 Copyright2019 by Xiaoyu Li
Dr.李晓瑜 Xiaoyu Li Email：xiaoyuuestc@uestc.edu.cn http://blog.sciencenet.cn/u/uestc2014xiaoyu 2019-Spring Lecture 3 Regression Analysis and Classification SunData Group http://www.sundatagroup.org/ School of Information and Software Engineering, UESTC Copyright © 2019 by Xiaoyu Li. 1
S3 Da t a G实o320 Content (8H) ATA 3.1 Learning Problems 3.2 The least square method (LSM) 3.3 Linear regression analysis .3.4 Classifications analysis 3.5 Other regression models 3 Copyright 2019 by Xiaoyu Li
Content（8H） 3.1 Learning Problems 3.2 The least square method (LSM) 3.3 Linear regression analysis 3.4 Classifications analysis 3.5 Other regression models Copyright © 2019 by Xiaoyu Li. 3
sunbata Groun Target Difference among the supervised learning, unsupervised learning and reinforcement learning. ·The principle of LSM. Linear regression models and applications. How to do the classification. 4 Copyright 2019 by Xiaoyu Li
Target Difference among the supervised learning, unsupervised learning and reinforcement learning. The principle of LSM. Linear regression models and applications. How to do the classification. Copyright © 2019 by Xiaoyu Li. 4
3.1 Learning Problems 5 DATA Copyright 2019 by Xiaoyu Li
Copyright © 2019 by Xiaoyu Li. 5 3.1 Learning Problems
(1)An insight of Learning 0 00 0 0 0 0 ● Q 0 ● 0 0 0 0 Kernel machines are used to compute a non-linearly separable functions into a higher dimension linearly separable function. DATA 6 Copyright 2019 by Xiaoyu Li
Copyright © 2019 by Xiaoyu Li. 6 （1） An insight of Learning Kernel machines are used to compute a non-linearly separable functions into a higher dimension linearly separable function
(2)Supervised Learning-1 ●Supervised Learning Task of inferring a function from labeled training data. The inferred function can be used for mapping new examples/unseen instances. Classical application: Regression of predicting numerical data; Classification of category labels; Predict sorting order. ·KNN,SVM DATA Copyright 2019 by Xiaoyu Li
Copyright © 2019 by Xiaoyu Li. 7 （2）Supervised Learning-1 Supervised Learning Task of inferring a function from labeled training data. The inferred function can be used for mapping new examples/ unseen instances. Classical application: Regression of predicting numerical data; Classification of category labels; Predict sorting order. KNN, SVM
(2)Supervised Learning-2 .Supervised Learning Process 1 Determine the type of training examples. .2 Gather a training set. 3 Determine the input feature representation of the learned function. .4 Determine the structure of the learned function and corresponding learning algorithm .5 Complete the design. 6 Evaluate the accuracy of the learned function. ATA 8 Copyright 2019 by Xiaoyu Li
Copyright © 2019 by Xiaoyu Li. 8 （2）Supervised Learning-2 Supervised Learning Process 1 Determine the type of training examples. 2 Gather a training set. 3 Determine the input feature representation of the learned function. 4 Determine the structure of the learned function and corresponding learning algorithm. 5 Complete the design. 6 Evaluate the accuracy of the learned function
(2)Supervised Learning-3 ●Supervised Learning YUPA DATA 9 Copyright 2019 by Xiaoyu Li
Copyright © 2019 by Xiaoyu Li. 9 （2）Supervised Learning-3 Supervised Learning
(3)Unsupervised Learning-1 Unsupervised Learning Trying to find hidden structure in unlabeled data. Clear or unclear task. No error or reward signal to evaluate a potential solution. ·Clustering .Anomaly detection 10 DATA Copyright 2019 by Xiaoyu Li
Copyright © 2019 by Xiaoyu Li. 10 （3）Unsupervised Learning-1 Unsupervised Learning Trying to find hidden structure in unlabeled data. Clear or unclear task. No error or reward signal to evaluate a potential solution. Clustering Anomaly detection
(3)Unsupervised Learning-2 Unsupervised Learning 11 DATA Copyright 2019 by Xiaoyu Li
Copyright © 2019 by Xiaoyu Li. 11 Unsupervised Learning （3）Unsupervised Learning-2
