Dive into a comprehensive course on statistical machine learning, covering fundamental concepts and advanced techniques. Begin with an introduction to probabilistic and statistical machine learning, then explore topics such as kNN classifiers, Bayesian decision theory, risk minimization, and linear regression. Progress to more complex subjects including support vector machines, kernel methods, random forests, and boosting. Examine dimensionality reduction techniques like PCA and t-SNE, as well as clustering algorithms. Delve into statistical learning theory, addressing convergence, consistency, and VC dimension. Conclude by exploring the societal impacts of machine learning, including fairness, explainability, and energy consumption. Gain practical knowledge through discussions on matrix completion, compressed sensing, and building effective machine learning pipelines.
Overview
Syllabus
Introduction - Probabilistic and Statistical Machine Learning 2020.
Statistical Machine Learning Part 1 - Machine learning and inductive bias.
Statistical Machine Learning Part 2 - Warmup: The kNN Classifier.
Statistical Machine Learning Part 3 - Formal setup, risk, consistency.
Statistical Machine Learning Part 4 - Bayesian decision theory.
Statistical Machine Learning Part 5: The Bayes classifier.
Statistical Machine Learning Part 6 - Risk minimization, approximation and estimation error.
Statistical Machine Learning Part 7a - What is a convex optimization problem?.
Statistical Machine Learning Part 7 - Linear least squares.
Statistical Machine Learning Part 8 - Feature representation.
Statistical Machine Learning Part 9 - Ridge regression.
Statistical Machine Learning Part 10 - Lasso.
Statistical Machine Learning Part 11 - Cross validation.
Statistical Machine Learning Part 12 - Risk minimization vs. probabilistic approaches.
Statistical Machine Learning Part 13 - Linear discriminant analysis.
Statistical Machine Learning Part 14 - Logistic regression.
Statistical Machine Learning Part 15 - Convex optimization, Lagrangian, dual problem.
Statistical Machine Learning Part 16 - Support vector machines: hard and soft margin.
Statistical Machine Learning Part 17 - Support vector machines: the dual problem.
Statistical Machine Learning Part 18 - Kernels: definitions and examples.
Statistical Machine Learning Part 19 - The reproducing kernel Hilbert space.
Statistical Machine Learning Part 20 - Kernel SVMs.
Statistical Machine Learning Part 21 - Kernelizing least squares regression.
Statistical Machine Learning Part 22 - How to center and normalize in feature space.
Statistical Machine Learning Part 23a - Random forests: building the trees.
Statistical Machine Learning Part 23b - Random forests: building the forests.
Statistical Machine Learning Part 24 - Boosting.
Statistical Machine Learning Part 25 - Principle Component Analysis.
Statistical Machine Learning Part 26 - Kernel PCA.
Statistical Machine Learning Part 27 - Multidimensional scaling.
Statistical Machine Learning Part 28 - Random projections and the Theorem of Johnson-Lindenstrauss.
Statistical Machine Learning Part 29 - Neighborhood graphs.
Statistical Machine Learning Part 30 - Isomap.
Statistical Machine Learning Part 31 - t-SNE.
Statistical Machine Learning Part 32 - Introduction to clustering.
Statistical Machine Learning Part 33 - k-means clustering.
Statistical Machine Learning Part 34 - Linkage algorithms for hierarchical clustering.
Statistical Machine Learning Part 35 - Spectral graph theory.
Statistical Machine Learning Part 36 - Spectral clustering, unnormalized case.
Statistical Machine Learning Part 37 - Spectral clustering: normalized, regularized.
Statistical Machine Learning Part 38 - Statistical learning theory: Convergence and consistency.
Statistical Machine Learning Part 39 - Statistical learning theory: finite function classes.
Statistical Machine Learning Part 40 - Statistical learning theory: shattering coefficient.
Statistical Machine Learning Part 41 - Statistical learning theory: VC dimension.
Statistical Machine Learning Part 42 - Statistical learning theory: Rademacher complexity.
Statistical Machine Learning Part 43 - Statistical learning theory: consistency of regularization.
Statistical Machine Learning Part 44 - Statistical learning theory: Revisiting Occam and outlook.
Statistical Machine Learning Part 45 - ML and Society: The general debate.
Statistical Machine Learning Part 46 - ML and Society: (Un)fairness in ML.
Statistical Machine Learning Part 47 - ML and Society: Formal approaches to fairness.
Statistical Machine Learning Part 48 - ML and Society: Algorithmic approaches to fairness.
Statistical Machine Learning Part 49 - ML and Society: Explainable ML.
Statistical Machine Learning Part 50 - ML and Society: The energy footprint of ML.
Statistical Machine Learning Part 51 - Low rank matrix completion: algorithms.
Statistical Machine Learning Part 52 - Low rank matrix completion: theory.
Statistical Machine Learning Part 53 - Compressed sensing.
Statistical Machine Learning Part 54 - ML pipeline: data, preprocessing, learning.
Statistical Machine Learning Part 55 - ML pipeline: evaluation.
Taught by
Tübingen Machine Learning
Tags
Related Courses
Related articles
Reviews
5.0 rating, based on 2 Class Central reviews
-
my thought over this is that videos are really good and make me able to learn every thing without any problem
-
I mean, this is deep, really great so far, i am only 20 minutes into it and I love it! I've seen all of the topics, everything that is needed in data science career is there.
