PPT-Design of Non-Linear Kernel Dictionaries for

Object Recognition Murad Megjhani MATH 6397 1 Agenda Sparse Coding Dictionary Learning Problem Formulation Kernel Results and Discussions 2 Motivation Given a 16x16or nxn image . Presented by: Johnathan Franck. Mentor: . Alex . Cloninger. Outline. Different Representations. 5 Techniques. Principal component . analysis (PCA)/. Multi-dimensional . scaling (MDS). Sammons non-linear mapping. Motivation: Image . denoising. How can we reduce noise in a photograph?. Let’s replace each pixel with a . weighted. average of its neighborhood. The weights are called the . filter kernel. What are the weights for the average of a . with Multiple Labels. Lei Tang. , . Jianhui. Chen and . Jieping. Ye. Kernel-based Methods. Kernel-based methods . Support Vector Machine (SVM). Kernel Linear Discriminate Analysis (KLDA). Demonstrate success in various domains. Motivation: Image . denoising. How can we reduce noise in a photograph?. Let’s replace each pixel with a . weighted. average of its neighborhood. The weights are called the . filter kernel. What are the weights for the average of a . A B M Shawkat Ali. 1. 2. Data Mining. ¤. . DM or KDD (Knowledge Discovery in Databases). Extracting previously unknown, valid, and actionable information . . . crucial decisions. ¤. . Approach. Presented by: Johnathan Franck. Mentor: . Alex . Cloninger. Outline. Different Representations. 5 Techniques. Principal component . analysis (PCA)/. Multi-dimensional . scaling (MDS). Sammons non-linear mapping. Jose C. . Principe. Computational . NeuroEngineering. . Laboratory (CNEL). University . of Florida. principe@cnel.ufl.edu. Acknowledgments. Dr. Weifeng Liu, Amazon. Dr. . Badong. Chen, . Tsinghua. University and Post Doc CNEL. nearest neighbor. Probabilistic models:. Naive Bayes. Logistic Regression. Linear models:. Perceptron. SVM. Decision models:. Decision Trees. Boosted Decision Trees. Random Forest. Outline: . a toolbox of useful algorithms concepts. with Analytical Models. Richard M. . Veras. , . Tze. . Meng. Low & Franz . Franchetti. Carnegie . Mellon . University . Tyler Smith & Robert van de . Geijn. University of Texas at . Austin. >>> inventory = {} # an empty dictionary. >>> inventory['apple'] = 6. >>> inventory['orange'] = 12. >>> inventory['banana'] = 4. >>> inventory['orange']. >>> inventory = {} # an empty dictionary. >>> inventory['apple'] = 6. >>> inventory['orange'] = 12. >>> inventory['banana'] = 4. >>> inventory['orange']. 3/6/15. Multiple linear regression. What are you predicting?. Data type. Continuous. Dimensionality. 1. What are you predicting it from?. Data type. Continuous. Dimensionality. p. How many data points do you have?. denoising. How can we reduce noise in a photograph?. Let’s replace each pixel with a . weighted. . average. of its neighborhood. The weights are called the . filter kernel. What are the weights for the average of a . Problems and Solutions. Classifying based . on similarities. :. 2. Van Gogh. Or. Monet. ?. Van Gogh. Monet. the Similarity-based Classification Problem. 3. (painter). (paintings). the Similarity-based Classification Problem.