Applied Machine Learning with Python

• - Data Integration for machine learning projects
• - Data processing for machine learning projects
• - Develop a full appreciation for neural networks and deep learning
• - Learn to choose between machine learning libraries
• - Use distributed machine learning, e.g.Spark MLib, when appropriate

When a developer applies machine learning in the real world, he needs how machine learning projects are conducted from soup to nuts, from the moment data have to be prepared for machine learning projects, up to the possibilities presented by deep learning libraries. Selections of machine learning algorithms are usually presented in beginners books, but then the context in which they are being used tends to be missing. This book is meant as a follow-up to introductory books on machine learning, and it will fill gaps like the preparation of machine learning data for ML projects, the variety and strengths of machine learning libraries, and how projects using neural networks and deep learning algorithms are actually executed. In other words, this book embeds what has been learned in theory and in small projects, in the real-world.

• - Develop a full appreciation of the big topics in Machine Learning, like when supervised or unsupervised learning is appropriate,
• - Stay away from partisanship with regard to libraries and learn to evaluate libraries solely according to their usefulness in a real-world context.
• - Show practical uses of deep learning
• – when can you use machine learning algorithms and when are deep learning algorithms appropriate- machine learning for business, not Kaggle competitions-