Download PDF HandsOn Unsupervised Learning Using Python How to Build Applied Machine Learning Solutions from Unlabeled Data Ankur A Patel 9781492035640 Books
Download As PDF : HandsOn Unsupervised Learning Using Python How to Build Applied Machine Learning Solutions from Unlabeled Data Ankur A Patel 9781492035640 Books
Many industry experts consider unsupervised learning the next frontier in artificial intelligence, one that may hold the key to the holy grail in AI research, the so-called general artificial intelligence. Since the majority of the world's data is unlabeled, conventional supervised learning cannot be applied; this is where unsupervised learning comes in. Unsupervised learning can be applied to unlabeled datasets to discover meaningful patterns buried deep in the data, patterns that may be near impossible for humans to uncover.
Author Ankur Patel provides practical knowledge on how to apply unsupervised learning using two simple, production-ready Python frameworks - scikit-learn and TensorFlow using Keras. With the hands-on examples and code provided, you will identify difficult-to-find patterns in data and gain deeper business insight, detect anomalies, perform automatic feature engineering and selection, and generate synthetic datasets. All you need is programming and some machine learning experience to get started.
- Compare the strengths and weaknesses of the different machine learning approaches supervised, unsupervised, and reinforcement learning
- Set up and manage a machine learning project end-to-end - everything from data acquisition to building a model and implementing a solution in production
- Use dimensionality reduction algorithms to uncover the most relevant information in data and build an anomaly detection system to catch credit card fraud
- Apply clustering algorithms to segment users - such as loan borrowers - into distinct and homogeneous groups
- Use autoencoders to perform automatic feature engineering and selection
- Combine supervised and unsupervised learning algorithms to develop semi-supervised solutions
- Build movie recommender systems using restricted Boltzmann machines
- Generate synthetic images using deep belief networks and generative adversarial networks
- Perform clustering on time series data such as electrocardiograms
- Explore the successes of unsupervised learning to date and its promising future
Download PDF HandsOn Unsupervised Learning Using Python How to Build Applied Machine Learning Solutions from Unlabeled Data Ankur A Patel 9781492035640 Books
"I've been looking to add more machine learning to my developer toolbox and this book was the absolute best thing I could find on the web. The author is NOT some professor who makes his living writing books, but a man at the edge of the space who has fought for the knowledge and experience in the real world.
I love how the book takes you from ground up implementing real systems in python. Not just unfinished snippets to show you how the m/l packages work (you can read their docs for that!) but he fills in the rest of the bigger picture which is "how do i make something that actually accomplishes a task in the world" your college prof probably has never had to ask that.
At $50 it's a steal, pickup a copy and don't look back."
Product details
|
Tags : Hands-On Unsupervised Learning Using Python How to Build Applied Machine Learning Solutions from Unlabeled Data [Ankur A. Patel] on . <div><span>Many industry experts consider unsupervised learning the next frontier in artificial intelligence,Ankur A. Patel,Hands-On Unsupervised Learning Using Python How to Build Applied Machine Learning Solutions from Unlabeled Data,O'Reilly Media,1492035645,AI; Keras; TensorFlow; artificial intelligence; big data; data science; deep learning; generative adversarial networks; intelligent machines; intelligent systems; machine learning; neural nets; neural networks; python; python machine learning; scikit-learn,AI;Keras;TensorFlow;artificial intelligence;big data;data science;deep learning;generative adversarial networks;intelligent machines;intelligent systems;machine learning;neural nets;neural networks;python;python machine learning,;scikit-learn,COMPUTER,COMPUTERS / Computer Vision Pattern Recognition,COMPUTERS / Data Processing,COMPUTERS / Intelligence (AI) Semantics,COMPUTERS / Machine Theory,COMPUTERS / Natural Language Processing,COMPUTERS / Neural Networks,COMPUTERS / Programming Languages / Python,Computer/General,Computers/Computer Vision Pattern Recognition,Computers/Intelligence (AI) Semantics,Computers/Machine Theory,Computers/Natural Language Processing,Computers/Neural Networks,Computers/Programming Languages - Python,Non-Fiction
HandsOn Unsupervised Learning Using Python How to Build Applied Machine Learning Solutions from Unlabeled Data Ankur A Patel 9781492035640 Books Reviews :
HandsOn Unsupervised Learning Using Python How to Build Applied Machine Learning Solutions from Unlabeled Data Ankur A Patel 9781492035640 Books Reviews
- This is a must-read for anyone interested in building AI applications. The introduction and conclusion are clear and informative, and the main content and code examples are forward thinking. All industry professionals, from data scientists to executives should read this book.
- I've been looking to add more machine learning to my developer toolbox and this book was the absolute best thing I could find on the web. The author is NOT some professor who makes his living writing books, but a man at the edge of the space who has fought for the knowledge and experience in the real world.
I love how the book takes you from ground up implementing real systems in python. Not just unfinished snippets to show you how the m/l packages work (you can read their docs for that!) but he fills in the rest of the bigger picture which is "how do i make something that actually accomplishes a task in the world" your college prof probably has never had to ask that.
At $50 it's a steal, pickup a copy and don't look back. - As an analyst trying to get more into the world of machine learning and python, I thought this was a great resource. I've been briefly exposed to a lot of the content in this book before, but this book does a great job of breaking concepts down with clear code examples and visualizations. I'd recommend this to any individuals or analytics teams trying to expand their knowledge of machine learning.
- Supervised Learning tends to receive far more coverage that Unsupervised Learning techniques, both in theory and practice. So it is common for many practicing data scientists to have a blind spot (comparatively speaking) with respect to knowledge of unsupervised learning techniques. This is unfortunate, since, as Yann Lecun points out with his cake analogy, much of the world's data is unlabeled and hence inaccessible to supervised learning techniques. This book attempts to remedy this, providing readers with a very accessible and techniques based introduction to popular unsupervised learning methods. Techniques covered include Dimensionality Reduction, Anomaly Detection, Clustering and Segmentation, Semi-supervised learning, Deep Learning based solutions using Autoencoders, Restricted Boltzmann Machines, Deep Belief Networks and Generative Adversarial Networks, Recommendation Systems and Time Series Clustering. Each technique is described and multiple solutions using various popular open source Python frameworks (scikit-learn, xgboost, lightgbm; fastcluster, hdbscan; tslearn; tensorflow and keras) are presented for each.
While having domain knowledge helps with any kind of data science work, it is especially important in case of unsupervised learning. This book doesn't (and realistically can't) help with that. That said, if you bring the domain knowledge, this book will give you the tools to work with the data and learn its distribution well enough to move the problem forward, often giving you tools to learn its distribution and automatically label it at scale, converting it to a supervised learning problem, where you can bring many more tools to bear on it.
In addition, the author also provides insights into various techniques for improving the quality of your unsupervised learning. The book also discusses a comprehensive evaluation framework used to evaluate the example solutions, which can be adapted for evaluating your own unsupervised learning solutions.
Overall, I think this is a very useful book, and provides a great resource for an area which hasn't been covered very well in the past. I have access to lots of text and image data through my work, but sadly very little of it is labeled, so while I am not an expert on unsupervised learning, I am not a newbie either. However, I am happy to report I also learned quite a few things from the book.
DISCLAIMER I did receive a complimentary copy of the book and a non-binding request to review if I could. I am reviewing the book because I believe it deserves attention. - Ankur provides a comprehensive yet very much accessible review of the current ML landscape; each chapter masterfully provides an intuition for the topic without being obscured by the sometimes complex mathematical machinery.
Moreover, he lays out the material in a simple “I do we do you do†pedagogical format. Starting with a foundational overview in each chapter, he then provides carefully curated guided examples followed by independent work. This allows the book to serve a dual purpose—as an invaluable learning tool for beginners but also as a succinct reference for practitioners.
