Discover all-practical implementations of the key algorithms and models for handling unlabelled data. Full of case studies demonstrating how to apply each technique to real-world problems. Models and Algorithms for Unlabeled Data introduces mathematical techniques, key algorithms, and Python implementations that will help you build machine learning models for unannotated data. Youโll master everything from kmeans and hierarchical clustering, to advanced neural networks like GANs and Restricted Boltzmann Machines. Youโll learn the business use case for different models, and master best practices for structured, text, and image data. Each new algorithm is introduced with a case study for retail, aviation, banking, and moreโand youโll develop a Python solution to fix each of these real-world problems. At the end of each chapter, youโll find quizzes, practice datasets, and links to research papers to help you lock in what youโve learned and expand your knowledge.
In Mastering Unlabeled Data youโll learn:
โข Fundamental building blocks and concepts of machine learning and unsupervised learning
โข Data cleaning for structured and unstructured data like text and images
โข Clustering algorithms like kmeans, hierarchical clustering, DBSCAN, Gaussian Mixture Models, and Spectral clustering
โข Dimensionality reduction methods like Principal Component Analysis (PCA), SVD, Multidimensional scaling, and t-SNE
โข Association rule algorithms like aPriori, ECLAT, SPADE
โข Unsupervised time series clustering, Gaussian Mixture models, and statistical methods
โข Building neural networks such as GANs and autoencoders
โข Dimensionality reduction methods like Principal Component Analysis and multidimensional scaling
โข Association rule algorithms like aPriori, ECLAT, and SPADE
โข Working with Python tools and libraries like sklearn, bumpy, Pandas, matplotlib, Seaborn, Keras, TensorFlow, and Flask
โข How to interpret the results of unsupervised learning
โข Choosing the right algorithm for your problem