What do you think?
Rate this book
Hands-On Unsupervised Learning with Python: Implement machine learning and deep learning models using Scikit-Learn, TensorFlow, and more
Discover the skill-sets required to implement various approaches to Machine Learning with Python
Key FeaturesExplore unsupervised learning with clustering, autoencoders, restricted Boltzmann machines, and moreBuild your own neural network models using modern Python librariesPractical examples show you how to implement different machine learning and deep learning techniquesBook DescriptionUnsupervised learning is about making use of raw, untagged data and applying learning algorithms to it to help a machine predict its outcome. With this book, you will explore the concept of unsupervised learning to cluster large sets of data and analyze them repeatedly until the desired outcome is found using Python.
This book starts with the key differences between supervised, unsupervised, and semi-supervised learning. You will be introduced to the best-used libraries and frameworks from the Python ecosystem and address unsupervised learning in both the machine learning and deep learning domains. You will explore various algorithms, techniques that are used to implement unsupervised learning in real-world use cases. You will learn a variety of unsupervised learning approaches, including randomized optimization, clustering, feature selection and transformation, and information theory. You will get hands-on experience with how neural networks can be employed in unsupervised scenarios. You will also explore the steps involved in building and training a GAN in order to process images.
By the end of this book, you will have learned the art of unsupervised learning for different real-world challenges.
What you will learnUse cluster algorithms to identify and optimize natural groups of dataExplore advanced non-linear and hierarchical clustering in actionSoft label assignments for fuzzy c-means and Gaussian mixture modelsDetect anomalies through density estimationPerform principal component analysis using neural network modelsCreate unsupervised models using GANsWho this book is forThis book is intended for statisticians, data scientists, machine learning developers, and deep learning practitioners who want to build smart applications by implementing key building block unsupervised learning, and master all the new techniques and algorithms offered in machine learning and deep learning using real-world examples. Some prior knowledge of machine learning concepts and statistics is desirable.
Table of ContentsGetting Started with Unsupervised LearningClustering FundamentalsAdvanced ClusteringHierarchical Clustering in ActionSoft Clustering and Gaussian Mixture ModelsAnomaly DetectionDimensionality Reduction and Component AnalysisUnsupervised Neural Network ModelsGenerative Adversarial Networks and SOMs
Key FeaturesExplore unsupervised learning with clustering, autoencoders, restricted Boltzmann machines, and moreBuild your own neural network models using modern Python librariesPractical examples show you how to implement different machine learning and deep learning techniquesBook DescriptionUnsupervised learning is about making use of raw, untagged data and applying learning algorithms to it to help a machine predict its outcome. With this book, you will explore the concept of unsupervised learning to cluster large sets of data and analyze them repeatedly until the desired outcome is found using Python.
This book starts with the key differences between supervised, unsupervised, and semi-supervised learning. You will be introduced to the best-used libraries and frameworks from the Python ecosystem and address unsupervised learning in both the machine learning and deep learning domains. You will explore various algorithms, techniques that are used to implement unsupervised learning in real-world use cases. You will learn a variety of unsupervised learning approaches, including randomized optimization, clustering, feature selection and transformation, and information theory. You will get hands-on experience with how neural networks can be employed in unsupervised scenarios. You will also explore the steps involved in building and training a GAN in order to process images.
By the end of this book, you will have learned the art of unsupervised learning for different real-world challenges.
What you will learnUse cluster algorithms to identify and optimize natural groups of dataExplore advanced non-linear and hierarchical clustering in actionSoft label assignments for fuzzy c-means and Gaussian mixture modelsDetect anomalies through density estimationPerform principal component analysis using neural network modelsCreate unsupervised models using GANsWho this book is forThis book is intended for statisticians, data scientists, machine learning developers, and deep learning practitioners who want to build smart applications by implementing key building block unsupervised learning, and master all the new techniques and algorithms offered in machine learning and deep learning using real-world examples. Some prior knowledge of machine learning concepts and statistics is desirable.
Table of ContentsGetting Started with Unsupervised LearningClustering FundamentalsAdvanced ClusteringHierarchical Clustering in ActionSoft Clustering and Gaussian Mixture ModelsAnomaly DetectionDimensionality Reduction and Component AnalysisUnsupervised Neural Network ModelsGenerative Adversarial Networks and SOMs
526 pages, Kindle Edition
Published February 28, 2019
3 people are currently reading
14 people want to read
About the author
Giuseppe Bonaccorso
18 books3 followersExperienced and goal-oriented senior executive leader with wide expertise in the management of Artificial Intelligence, Machine Learning, Deep Learning, and Data Science projects for healthcare, B2C and Military industries (Fortune 500 firms).
His main interests include Machine/Deep Learning, Reinforcement Learning, Advanced Analytics, Bio-inspired adaptive systems, Business Intelligence, Neuroscience, Neural Language Processing, Econometrics, Data Science Strategy and Organization.
Professional member of IEEE, IEEE Computer Society, AAAI, ACM, IAENG, AICA, SFIA, and Agile Manifesto.
His main interests include Machine/Deep Learning, Reinforcement Learning, Advanced Analytics, Bio-inspired adaptive systems, Business Intelligence, Neuroscience, Neural Language Processing, Econometrics, Data Science Strategy and Organization.
Professional member of IEEE, IEEE Computer Society, AAAI, ACM, IAENG, AICA, SFIA, and Agile Manifesto.
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
Displaying 1 - 2 of 2 reviews
September 27, 2022
Unsupervised Miners
This was another very impressive scientific computer science book. It really put the science in computer science.
I learned a lot, and got a lot of really neat deep learning models and coding examples from it.
I even adopted some of the ideas in the book for some of my own unsupervised data mining ML projects.
Would highly recommend this one as well!
4.8/5
This was another very impressive scientific computer science book. It really put the science in computer science.
I learned a lot, and got a lot of really neat deep learning models and coding examples from it.
I even adopted some of the ideas in the book for some of my own unsupervised data mining ML projects.
Would highly recommend this one as well!
4.8/5
March 31, 2023
This wasn't a bad book And it certainly covered a lot of ground. This said, the book suffers from a primary flaw of most introductory text on a subject. It refers the Reader to a referenced paper/book which describes/motivates a concept/topic, using only terse terminology or mathematically symbolism (not even added into the OCR text of book) to describe a "well-known" concept. Also, the examples are contrived and use random generated data (mostly) as input to the unsupervised learning models and a graphical output or scaler vector to describe the resultant performance. This leaves the reader with a reference book which might be helpful but is certainly Not an introduction and Explanation of techniques and their application in real-world. It maybe that the author was simple covering the bases of the field of study But IMO we don't need more of these. The world needs more books which convey comprehensive understanding of a technology to the reader. If you're looking for that in this book, you likely will not find it (without reading all the references provided).
Displaying 1 - 2 of 2 reviews