Oreilly – Data Without Labels, Video Edition 2025-5

Updated August 10, 2026 1.6 GB

Download

About this item

Description

Data Without Labels, Video Edition. This course is a comprehensive guide to unsupervised learning that explores the mathematical foundations, key algorithms, and practical applications of the field. With a focus on practical implementation, this course introduces participants to the techniques and Python coding needed to build machine learning models based on unlabeled data. The course content is designed around real-world industry case studies and demonstrates how each technique can be applied to solve real-world problems. The course bridges the gap between complex mathematical concepts and practical implementation, covering the entire model development process from start to finish through deployment in an operational environment. Participants will explore unsupervised learning approaches that can be used to understand raw datasets and support strategic business decisions. Numerous business applications are explored in this course, including generative AI, predictive algorithms, and fraud detection. The main focus is on transforming raw text, image, and numerical data into valuable insights about customers, building accurate computer vision systems, and generating high-quality datasets for training AI models. Practical examples from industries such as retail, aviation, and banking are presented using fully explained Python code. Basic topics from clustering and dimensionality reduction to more advanced topics such as autoencoders and generative adversarial networks are covered in this course.

What you will learn

The building blocks and basic concepts of machine learning and unsupervised learning.
Data cleansing for structured and unstructured data such as text and images.
Clustering algorithms such as K-means, hierarchical clustering, DBSCAN, Gaussian Mixture Models, and Spectral clustering.
Dimensionality reduction methods such as principal component analysis (PCA), SVD, multidimensional scaling, and t-SNE.
Association rule algorithms such as aPriori, ECLAT, and SPADE.
Unsupervised time series clustering, Gaussian Mixture models, and statistical methods.
Building neural networks such as GANs and autoencoders.
Working with Python tools and libraries such as sci-kit learn, numpy, Pandas, matplotlib, Seaborn, Keras, TensorFlow, and Flask.
How to interpret unsupervised learning results.
Choosing the right algorithm for the problem at hand.
Deploying unsupervised learning in an operational environment.
Maintaining and updating the machine learning solution (ML solution).
Real-world commercial and business applications for unsupervised learning.
How to create and refine training datasets for artificial intelligence (AI).