1 / 11

Welcome to the Kernel-Class

Welcome to the Kernel-Class. My name : Max (Welling) Book: There will be class-notes/slides. Homework : reading material, some exercises, some MATLAB implementations. I like : an active attitude in class. ask questions! respond to my questions. Enjoy.

mardi
Télécharger la présentation

Welcome to the Kernel-Class

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Welcome to the Kernel-Class • My name: Max (Welling) • Book: • There will be class-notes/slides. • Homework: reading material, some exercises, some MATLAB implementations. • I like: an active attitude in class. ask questions! respond to my questions. • Enjoy.

  2. Primary Goal • What is the primary goal of: • - Machine Learning • - Data Mining • - Pattern Recognition • - Data Analysis • - Statistics • Automatic detection of non-coincidental structure in data.

  3. Desiderata • Robust algorithms are insensitive to outliers and wrong • model assumptions. • Stable algorithms: generalize well to unseen data. • Computationally efficient algorithms are necessary to handle • large datasets.

  4. Supervised & Unsupervised Learning • supervised: classification, regression • unsupervised: clustering, dimensionality reduction, ranking, • outlier detection. • primal vs. dual problems: generalized linear models vs. • kernel classification. this is like nearest neighbor classification.

  5. Feature Spaces non-linear mapping to F 1. high-D space 2. infinite-D countable space : 3. function space (Hilbert space) example:

  6. Kernel Trick Note: In the dual representation we used the Gram matrix to express the solution. Kernel Trick: Replace : kernel If we use algorithms that only depend on the Gram-matrix, G, then we never have to know (compute) the actual features This is the crucial point of kernel methods

  7. Properties of a Kernel Definition:A finitely positive semi-definite function is a symmetric function of its arguments for which matrices formed by restriction on any finite subset of points is positive semi-definite. Theorem:A function can be written as where is a feature map iff k(x,y) satisfies the semi-definiteness property. Relevance: We can now check if k(x,y) is a proper kernel using only properties of k(x,y) itself, i.e. without the need to know the feature map!

  8. Modularity Kernel methods consist of two modules: 1) The choice of kernel (this is non-trivial) 2) The algorithm which takes kernels as input Modularity: Any kernel can be used with any kernel-algorithm. some kernel algorithms: - support vector machine - Fisher discriminant analysis - kernel regression - kernel PCA - kernel CCA some kernels:

  9. Goodies and Baddies • Goodies: • Kernel algorithms are typically constrained convex optimization • problems  solved with either spectral methods or convex optimization tools. • Efficient algorithms do exist in most cases. • The similarity to linear methods facilitates analysis. There are strong • generalization bounds on test error. • Baddies: • You need to choose the appropriate kernel • Kernel learning is prone to over-fitting • All information must go through the kernel-bottleneck.

  10. Regularization • regularization is very important! • regularization parameters determined by out of sample. • measures (cross-validation, leave-one-out). Demo Trevor Hastie.

  11. Learning Kernels • All information is tunneled through the Gram-matrix information • bottleneck. • The real art is to pick an appropriate kernel. • e.g. take the RBF kernel: if c is very small: G=I (all data are dissimilar): over-fitting if c is very large: G=1 (all data are very similar): under-fitting We need to learn the kernel. Here is some ways to combine kernels to improve them: cone k1 k2 any positive polynomial

More Related