"Real-World Machine Learning" is a book that covers the practical aspects of building machine learning systems for real-world applications. The book was written by Henrik Brink, Joseph Richards, and Mark Fetherolf, who are experienced machine learning practitioners.
The book is divided into three parts:
Introduction to Machine Learning: This section covers the basics of machine learning, including supervised and unsupervised learning, overfitting, and underfitting. It also covers common machine learning algorithms, such as decision trees, k-nearest neighbors, and linear regression.
Real-World Machine Learning: This section covers the practical aspects of building machine learning systems for real-world applications. It covers topics such as data preprocessing, feature selection, model selection, and model evaluation. It also covers the use of deep learning algorithms for image and text analysis.
Advanced Topics in Machine Learning: This section covers advanced topics in machine learning, such as reinforcement learning, time series analysis, and anomaly detection. It also covers the use of machine learning in specific domains, such as recommender systems and fraud detection.
The book provides practical examples and code snippets using popular machine learning libraries, such as scikit-learn and TensorFlow. It also covers best practices for building machine learning systems, such as data preparation, model tuning, and error analysis.
"Real-World Machine Learning" is suitable for machine learning practitioners, data scientists, and software developers who are interested in building machine learning systems for real-world applications. The book assumes some familiarity with machine learning concepts and programming.
