In those years, I learned the main contents of machine learning:
1. Basic introduction to machine learning, getting started with machine learning; 2. Linear regression and logistic. XX Performance Prediction System, intelligent interactive statistical system, etc. 3. Ridge regression, Lasso, variable selection techniques. Techniques such as dimension techniques; 4. dimensionality reduction Technology. XX indicator design, specific specifications; 5. Linear classifier, KNN algorithm, naive Bayesian classifier, text mining. XX intelligent spam message, spam judgment, Comment intelligent analysis, intelligent monitoring and statistical warning system AH. 6. Decision tree, combined lifting algorithm, bagging and adaboost, random forest. XX User Analysis System, intelligent advertising push system. 7. Support Vector machine. Understand the principles and mechanisms of SVM. 8. Artificial neural networks. It's good to get up, actually, that's it! What single layer perceptron, what linear neural network, what BP neural network, what is based on gradient descent learning algorithm and image compression technology. 9. Universal Approximation radial basis function neural network. I've heard "character recognition, face recognition"! These technologies involve PDAs and SVM. Yes, there are hopfield associative memory neural networks. 10. Probabilistic neural networks and Faith Bayesian classifier 11. Clustering, isolated point discrimination. This technology is very practical, can be applied to what advertising recommendation system, network anti-cheating recognition and so on.
Machine Learning Knowledge System