Applied machine learning with a solid foundation in theory. Revised and expanded for TensorFlow 2, GANs, and reinforcement learning.
Key Features
• Third edition of the bestselling, widely acclaimed Python machine learning book
• Clear and intuitive explanations take you deep into the theory and practice of Python machine learning
• Fully updated and expanded to cover TensorFlow 2, Generative Adversarial Network models, reinforcement learning, and best practices
Book Description
Python Machine Learning, Third Edition is a comprehensive guide to machine learning and deep learning with Python. It acts as both a step-by-step tutorial, and a reference you'll keep coming back to as you build your machine learning systems.
Packed with clear explanations, visualizations, and working examples, the book covers all the essential machine learning techniques in depth. While some books teach you only to follow instructions, with this machine learning book, Raschka and Mirjalili teach the principles behind machine learning, allowing you to build models and applications for yourself.
Updated for TensorFlow 2.0, this new third edition introduces readers to its new Keras API features, as well as the latest additions to scikit-learn. It's also expanded to cover cutting-edge reinforcement learning techniques based on deep learning, as well as an introduction to GANs. Finally, this book also explores a subfield of natural language processing (NLP) called sentiment analysis, helping you learn how to use machine learning algorithms to classify documents.
This book is your companion to machine learning with Python, whether you're a Python developer new to machine learning or want to deepen your knowledge of the latest developments.
What you will learn
• Master the frameworks, models, and techniques that enable machines to 'learn' from data
• Use scikit-learn for machine learning and TensorFlow for deep learning
• Apply machine learning to image classification, sentiment analysis, intelligent web applications, and more
• Build and train neural networks, GANs, and other models
• Discover best practices for evaluating and tuning models
• Predict continuous target outcomes using regression analysis
• Dig deeper into textual and social media data using sentiment analysis
Who This Book Is For
If you know some Python and you want to use machine learning and deep learning, pick up this book. Whether you want to start from scratch or extend your machine learning knowledge, this is an essential resource. Written for developers and data scientists who want to create practical machine learning and deep learning code, this book is ideal for anyone who wants to teach computers how to learn from data.

lgrsnf/Z:\Bibliotik_\A Library\Machine Learning\Python Machine Learning, 3rd Edition by Sebastian Raschka\Python Machine Learning Machine Learning and Deep Learning with Python, 3rd Edition.pdf

nexusstc/Python Machine Learning: Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow 2/c2ff5355cf41fa2a82bdfb0ed900c49c.pdf

zlib/Computers/Computer Science/Raschka, Sebastian;Mirjalili, Vahid/Python Machine Learning: Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow 2, 3rd Edition_11061404.pdf

Python и машинное обучение: машинное и глубокое обучение с использованием Python, scikit-learn и TensorFlow 2: [охватывает TensorFlow 2, порождающие состязательные сети и обучение с подкреплением]

AI Crash Course : A Fun and Hands-on Introduction to Machine Learning, Reinforcement Learning, Deep Learning, and Artificial Intelligence with Python

Dancing with Qubits : How Quantum Computing Works and How It Can Change the World

Computer Vision (ICCV), 2015 IEEE International Conference on

2015 Ieee International Conference On Computer Vision

Себастьян Рашка, Вахид Мирджалили; перевод с английского и редакция Ю. Н. Артеменко

Sebastian Raschka; Vahid Mirjalili

Ponteves, Hadelin de

Hadelin de Ponteves

Sutor, Robert S.

Рашка, Себастьян

Robert S. Sutor

Packt Publishing, Limited; Packt Publishing

California Department of Education

Dorling Kindersley Publishers Ltd

US ISBN Agency Issue Account

Riverside Publishing Company

Диалектика; Диалектика

Ladybird Books Ltd

Мнение экспертов, 3-е изд., Москва, Санкт-Петербург, Russia, 2020

United Kingdom and Ireland, United Kingdom

United States, United States of America

Packt Publishing, Birmingham, UK, 2019

Expert insight, Birmingham, UK, 2019

Third edition, Birmingham, 2019

Packt Publishing, [S.l.], 2019

3rd ed, Birmingham, 2020

1st edition, 2019

Dec 12, 2019

2019-11-28

2015

lg2867142

{"edition":"3","isbns":["0145682102","0392405660","0801165040","0829280731","1467383910","1789955750","1789958296","1838645357","1838827366","9780145682101","9780392405669","9780801165047","9780829280739","9781467383912","9781789955750","9781789958294","9781838645359","9781838827366"],"last_page":770,"publisher":"Packt Publishing - ebooks Account"}

类型: 图书

出版日期: 2019

出版社: Packt Publishing

Source title: Python Machine Learning: Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow 2, 3rd Edition

Предм. указ.: с. 835-846
Пер.: Raschka, Sebastian Python machine learning Birmingham, Mumbai : Packt, cop. 2019 978-1-78995-575-0

РГБ

Russian State Library [rgb] MARC:
=001 010476613
=005 20201125120140.0
=008 201109s2020\\\\ru\||||\\\\\\\0||\|\rus|d
=017 \\ $a КН-П-20-071013 $b RuMoRKP
=020 \\ $a 978-5-907203-57-0 $c 500 экз.
=040 \\ $a RuMoRGB $b rus $e rcr
=041 1\ $a rus $h eng
=044 \\ $a ru
=084 \\ $a З973.236-018.19Python,07 $2 rubbk
=100 1\ $a Рашка, Себастьян
=245 00 $a Python и машинное обучение : $b машинное и глубокое обучение с использованием Python, scikit-learn и TensorFlow 2 : [охватывает TensorFlow 2, порождающие состязательные сети и обучение с подкреплением] $c Себастьян Рашка, Вахид Мирджалили ; перевод с английского и редакция Ю. Н. Артеменко
=250 \\ $a 3-е изд.
=260 \\ $a Москва $b Диалектика ; $a Санкт-Петербург $b Диалектика $c 2020
=300 \\ $a 846 с. $b ил., табл. $c 24 см
=336 \\ $a Текст (визуальный)
=337 \\ $a непосредственный
=490 0\ $a Мнение экспертов
=500 \\ $a Предм. указ.: с. 835-846
=534 \\ $p Пер.: $a Raschka, Sebastian $t Python machine learning $c Birmingham, Mumbai : Packt, cop. 2019 $z 978-1-78995-575-0
=650 \7 $a Техника. Технические науки -- Энергетика. Радиоэлектроника -- Энергетика -- Вычислительная техника -- Вычислительные машины электронные цифровые -- Обучающие машины -- Языки программирования -- Python -- Пособие для специалистов $2 rubbk
=653 \\ $a Pithon
=653 \\ $a scikit-learn
=653 \\ $a TensorFlow 2
=700 1\ $a Мирджалили, Вахид
=852 \\ $a РГБ $b FB $j 2 20-59/140 $x 90
=852 7\ $a РГБ $b CZ2 $h З-813/Р28 $x 83

Cover......Page 1
Copyright......Page 3
Packt Page......Page 4
Contributors......Page 5
Table of Contents......Page 8
Preface......Page 20
Building intelligent machines to transform data into knowledge......Page 30
The three different types of machine learning......Page 31
Classification for predicting class labels......Page 32
Regression for predicting continuous outcomes......Page 33
Solving interactive problems with reinforcement learning......Page 35
Finding subgroups with clustering......Page 36
Introduction to the basic terminology and notations......Page 37
Notation and conventions used in this book......Page 38
A roadmap for building machine learning systems......Page 40
Preprocessing – getting data into shape......Page 41
Training and selecting a predictive model......Page 42
Installing Python and packages from the Python Package Index......Page 43
Using the Anaconda Python distribution and package manager......Page 44
Summary......Page 45
Chapter 2: Training Simple Machine Learning Algorithms for Classification......Page 48
Artificial neurons – a brief glimpse into the early history of machine learning......Page 49
The formal definition of an artificial neuron......Page 50
The perceptron learning rule......Page 52
An object-oriented perceptron API......Page 55
Training a perceptron model on the Iris dataset......Page 59
Adaptive linear neurons and the convergence of learning......Page 65
Minimizing cost functions with gradient descent......Page 66
Implementing Adaline in Python......Page 69
Improving gradient descent through feature scaling......Page 73
Large-scale machine learning and stochastic gradient descent......Page 75
Summary......Page 80
Choosing a classification algorithm......Page 82
First steps with scikit-learn – training a perceptron......Page 83
Logistic regression and conditional probabilities......Page 89
Learning the weights of the logistic cost function......Page 94
Converting an Adaline implementation into an algorithm for logistic regression......Page 96
Training a logistic regression model with scikit-learn......Page 101
Tackling overfitting via regularization......Page 104
Maximum margin intuition......Page 108
Dealing with a nonlinearly separable case using slack variables......Page 110
Alternative implementations in scikit-learn......Page 112
Kernel methods for linearly inseparable data......Page 113
Using the kernel trick to find separating hyperplanes in a high-dimensional space......Page 115
Decision tree learning......Page 119
Maximizing IG – getting the most bang for your buck......Page 120
Building a decision tree......Page 125
Combining multiple decision trees via random forests......Page 129
K-nearest neighbors – a lazy learning algorithm......Page 132
Summary......Page 137
Dealing with missing data......Page 138
Identifying missing values in tabular data......Page 139
Eliminating training examples or features with missing values......Page 140
Imputing missing values......Page 141
Understanding the scikit-learn estimator API......Page 142
Handling categorical data......Page 144
Mapping ordinal features......Page 145
Encoding class labels......Page 146
Performing one-hot encoding on nominal features......Page 147
Partitioning a dataset into separate training and test datasets......Page 150
Bringing features onto the same scale......Page 153
Selecting meaningful features......Page 156
A geometric interpretation of L2 regularization......Page 157
Sparse solutions with L1 regularization......Page 160
Sequential feature selection algorithms......Page 164
Assessing feature importance with random forests......Page 170
Summary......Page 172
Unsupervised dimensionality reduction via principal component analysis......Page 174
The main steps behind principal component analysis......Page 175
Extracting the principal components step by step......Page 177
Total and explained variance......Page 180
Feature transformation......Page 181
Principal component analysis in scikit-learn......Page 184
Principal component analysis versus linear discriminant analysis......Page 188
The inner workings of linear discriminant analysis......Page 189
Computing the scatter matrices......Page 190
Selecting linear discriminants for the new feature subspace......Page 193
Projecting examples onto the new feature space......Page 196
LDA via scikit-learn......Page 197
Using kernel principal component analysis for nonlinear mappings......Page 198
Kernel functions and the kernel trick......Page 199
Implementing a kernel principal component analysis in Python......Page 204
Example 1 – separating half-moon shapes......Page 206
Example 2 – separating concentric circles......Page 209
Projecting new data points......Page 212
Kernel principal component analysis in scikit-learn......Page 216
Summary......Page 217
Streamlining workflows with pipelines......Page 220
Loading the Breast Cancer Wisconsin dataset......Page 221
Combining transformers and estimators in a pipeline......Page 222
Using k-fold cross-validation to assess model performance......Page 224
The holdout method......Page 225
K-fold cross-validation......Page 226
Diagnosing bias and variance problems with learning curves......Page 230
Addressing over- and underfitting with validation curves......Page 234
Tuning hyperparameters via grid search......Page 236
Algorithm selection with nested cross-validation......Page 238
Reading a confusion matrix......Page 240
Optimizing the precision and recall of a classification model......Page 242
Plotting a receiver operating characteristic......Page 245
Scoring metrics for multiclass classification......Page 248
Dealing with class imbalance......Page 249
Summary......Page 251
Learning with ensembles......Page 252
Combining classifiers via majority vote......Page 256
Implementing a simple majority vote classifier......Page 257
Using the majority voting principle to make predictions......Page 263
Evaluating and tuning the ensemble classifier......Page 266
Bagging – building an ensemble of classifiers from bootstrap samples......Page 272
Bagging in a nutshell......Page 273
Applying bagging to classify examples in the Wine dataset......Page 274
Leveraging weak learners via adaptive boosting......Page 278
How boosting works......Page 279
Applying AdaBoost using scikit-learn......Page 283
Summary......Page 286
Preparing the IMDb movie review data for text processing......Page 288
Preprocessing the movie dataset into a more convenient format......Page 289
Introducing the bag-of-words model......Page 291
Transforming words into feature vectors......Page 292
Assessing word relevancy via term frequency-inverse document frequency......Page 294
Cleaning text data......Page 296
Processing documents into tokens......Page 298
Training a logistic regression model for document classification......Page 301
Working with bigger data – online algorithms and out-of-core learning......Page 303
Topic modeling with Latent Dirichlet Allocation......Page 307
LDA with scikit-learn......Page 308
Summary......Page 312
Serializing fitted scikit-learn estimators......Page 314
Setting up an SQLite database for data storage......Page 318
Developing a web application with Flask......Page 320
Our first Flask web application......Page 321
Form validation and rendering......Page 323
Setting up the directory structure......Page 324
Adding style via CSS......Page 325
Creating the result page......Page 327
Turning the movie review classifier into a web application......Page 329
Files and folders – looking at the directory tree......Page 330
Implementing the main application as app.py......Page 331
Setting up the review form......Page 334
Creating a results page template......Page 335
Creating a PythonAnywhere account......Page 338
Uploading the movie classifier application......Page 339
Updating the movie classifier......Page 340
Summary......Page 343
Introducing linear regression......Page 344
Simple linear regression......Page 345
Multiple linear regression......Page 346
Loading the Housing dataset into a data frame......Page 347
Visualizing the important characteristics of a dataset......Page 349
Looking at relationships using a correlation matrix......Page 351
Solving regression for regression parameters with gradient descent......Page 354
Estimating the coefficient of a regression model via scikit-learn......Page 359
Fitting a robust regression model using RANSAC......Page 361
Evaluating the performance of linear regression models......Page 363
Using regularized methods for regression......Page 366
Turning a linear regression model into a curve – polynomial regression......Page 368
Adding polynomial terms using scikit-learn......Page 369
Modeling nonlinear relationships in the Housing dataset......Page 371
Dealing with nonlinear relationships using random forests......Page 374
Decision tree regression......Page 375
Random forest regression......Page 377
Summary......Page 379
Grouping objects by similarity using k-means......Page 382
K-means clustering using scikit-learn......Page 383
A smarter way of placing the initial cluster centroids using k-means++......Page 387
Hard versus soft clustering......Page 388
Using the elbow method to find the optimal number of clusters......Page 390
Quantifying the quality of clustering via silhouette plots......Page 392
Organizing clusters as a hierarchical tree......Page 396
Grouping clusters in bottom-up fashion......Page 397
Performing hierarchical clustering on a distance matrix......Page 398
Attaching dendrograms to a heat map......Page 402
Applying agglomerative clustering via scikit-learn......Page 404
Locating regions of high density via DBSCAN......Page 405
Summary......Page 411
Modeling complex functions with artificial neural networks......Page 412
Single-layer neural network recap......Page 414
Introducing the multilayer neural network architecture......Page 416
Activating a neural network via forward propagation......Page 420
Classifying handwritten digits......Page 422
Obtaining and preparing the MNIST dataset......Page 423
Implementing a multilayer perceptron......Page 429
Computing the logistic cost function......Page 441
Developing your understanding of backpropagation......Page 444
Training neural networks via backpropagation......Page 446
About the convergence in neural networks......Page 450
A few last words about the neural network implementation......Page 451
Summary......Page 452
Chapter 13: Parallelizing Neural Network Training with TensorFlow......Page 454
Performance challenges......Page 455
What is TensorFlow?......Page 456
Installing TensorFlow......Page 458
Creating tensors in TensorFlow......Page 459
Manipulating the data type and shape of a tensor......Page 460
Applying mathematical operations to tensors......Page 461
Split, stack, and concatenate tensors......Page 463
Building input pipelines using tf.data – the TensorFlow Dataset API......Page 464
Creating a TensorFlow Dataset from existing tensors......Page 465
Combining two tensors into a joint dataset......Page 466
Shuffle, batch, and repeat......Page 468
Creating a dataset from files on your local storage disk......Page 470
Fetching available datasets from the tensorflow_datasets library......Page 474
Building an NN model in TensorFlow......Page 479
Building a linear regression model......Page 480
Model training via the .compile() and .fit() methods......Page 485
Building a multilayer perceptron for classifying flowers in the Iris dataset......Page 486
Saving and reloading the trained model......Page 490
Choosing activation functions for multilayer neural networks......Page 491
Logistic function recap......Page 492
Estimating class probabilities in multiclass classification via the softmax function......Page 494
Broadening the output spectrum using a hyperbolic tangent......Page 495
Rectified linear unit activation......Page 497
Summary......Page 499
Chapter 14: Going Deeper – The Mechanics of TensorFlow......Page 500
The key features of TensorFlow......Page 501
Understanding computation graphs......Page 502
Creating a graph in TensorFlow v1.x......Page 503
Migrating a graph to TensorFlow v2......Page 504
Loading input data into a model: TensorFlow v2 style......Page 505
Improving computational performance with function decorators......Page 506
TensorFlow Variable objects for storing and updating model parameters......Page 508
Computing the gradients of the loss with respect to trainable variables......Page 512
Keeping resources for multiple gradient computations......Page 514
Simplifying implementations of common architectures via the Keras API......Page 515
Solving an XOR classification problem......Page 518
Making model building more flexible with Keras' functional API......Page 523
Implementing models based on Keras' Model class......Page 525
Writing custom Keras layers......Page 526
Working with feature columns......Page 530
Machine learning with pre-made Estimators......Page 535
Using Estimators for MNIST handwritten digit classification......Page 539
Creating a custom Estimator from an existing Keras model......Page 541
Summary......Page 544
Chapter 15: Classifying Images with Deep Convolutional Neural Networks......Page 546
Understanding CNNs and feature hierarchies......Page 547
Performing discrete convolutions......Page 549
Discrete convolutions in one dimension......Page 550
Padding inputs to control the size of the output feature maps......Page 552
Determining the size of the convolution output......Page 554
Performing a discrete convolution in 2D......Page 555
Subsampling layers......Page 559
Working with multiple input or color channels......Page 561
Regularizing an NN with dropout......Page 565
Loss functions for classification......Page 568
The multilayer CNN architecture......Page 571
Loading and preprocessing the data......Page 572
Configuring CNN layers in Keras......Page 573
Constructing a CNN in Keras......Page 574
Gender classification from face images using a CNN......Page 579
Loading the CelebA dataset......Page 580
Image transformation and data augmentation......Page 581
Training a CNN gender classifier......Page 587
Summary......Page 593
Chapter 16: Modeling Sequential Data Using Recurrent Neural Networks......Page 596
Modeling sequential data—order matters......Page 597
Representing sequences......Page 598
The different categories of sequence modeling......Page 599
Understanding the RNN looping mechanism......Page 600
Computing activations in an RNN......Page 603
Hidden-recurrence versus output-recurrence......Page 606
The challenges of learning long-range interactions......Page 609
Long short-term memory cells......Page 611
Implementing RNNs for sequence modeling in TensorFlow......Page 613
Preparing the movie review data......Page 614
Embedding layers for sentence encoding......Page 619
Building an RNN model......Page 621
Building an RNN model for the sentiment analysis task......Page 623
Project two: character-level language modeling in TensorFlow......Page 629
Preprocessing the dataset......Page 630
Building a character-level RNN model......Page 636
Evaluation phase: generating new text passages......Page 638
Understanding language with the Transformer model......Page 642
A basic version of self-attention......Page 643
Parameterizing the self-attention mechanism with query, key, and value weights......Page 645
Multi-head attention and the Transformer block......Page 646
Summary......Page 647
Chapter 17: Generative Adversarial Networks for Synthesizing New Data......Page 648
Starting with autoencoders......Page 649
Generative models for synthesizing new data......Page 652
Generating new samples with GANs......Page 653
Understanding the loss functions of the generator and discriminator networks in a GAN model......Page 655
Training GAN models on Google Colab......Page 657
Implementing the generator and the discriminator networks......Page 660
Defining the training dataset......Page 665
Training the GAN model......Page 667
Improving the quality of synthesized images using a convolutional and Wasserstein GAN......Page 675
Transposed convolution......Page 676
Batch normalization......Page 677
Implementing the generator and discriminator......Page 680
Dissimilarity measures between two distributions......Page 686
Using EM distance in practice for GANs......Page 690
Gradient penalty......Page 691
Implementing WGAN-GP to train the DCGAN model......Page 692
Mode collapse......Page 696
Other GAN applications......Page 698
Summary......Page 699
Chapter 18: Reinforcement Learning for Decision Making in Complex Environments......Page 700
Understanding reinforcement learning......Page 701
Defining the agent-environment interface of a reinforcement learning system......Page 703
Markov decision processes......Page 705
The mathematical formulation of Markov decision processes......Page 706
Visualization of a Markov process......Page 708
The return......Page 709
Policy......Page 711
Value function......Page 712
Dynamic programming using the Bellman equation......Page 714
Dynamic programming......Page 715
Policy evaluation – predicting the value function with dynamic programming......Page 716
Policy iteration......Page 717
Reinforcement learning with Monte Carlo......Page 718
Action-value function estimation using MC......Page 719
Temporal difference learning......Page 720
TD prediction......Page 721
On-policy TD control (SARSA)......Page 722
Implementing our first RL algorithm......Page 723
Working with the existing environments in OpenAI Gym......Page 724
A grid world example......Page 726
Implementing the grid world environment in OpenAI Gym......Page 727
Implementing the Q-learning algorithm......Page 734
A glance at deep Q-learning......Page 738
Training a DQN model according to the Q-learning algorithm......Page 739
Implementing a deep Q-learning algorithm......Page 741
Chapter and book summary......Page 746
Other Books You May Enjoy......Page 750
Index......Page 754

<p><b>Applied machine learning with a solid foundation in theory. Revised and expanded for TensorFlow 2, GANs, and reinforcement learning.</b></p><h4>Key Features</h4><ul><li>Third edition of the bestselling, widely acclaimed Python machine learning book</li><li>Clear and intuitive explanations take you deep into the theory and practice of Python machine learning</li><li>Fully updated and expanded to cover TensorFlow 2, Generative Adversarial Network models, reinforcement learning, and best practices</li></ul><h4>Book Description</h4><p>Python Machine Learning, Third Edition is a comprehensive guide to machine learning and deep learning with Python. It acts as both a step-by-step tutorial, and a reference you'll keep coming back to as you build your machine learning systems.</p><p>Packed with clear explanations, visualizations, and working examples, the book covers all the essential machine learning techniques in depth. While some books teach you only to follow instructions, with this machine learning book, Raschka and Mirjalili teach the principles behind machine learning, allowing you to build models and applications for yourself.</p><p>Updated for TensorFlow 2.0, this new third edition introduces readers to its new Keras API features, as well as the latest additions to scikit-learn. It's also expanded to cover cutting-edge reinforcement learning techniques based on deep learning, as well as an introduction to GANs. Finally, this book also explores a subfield of natural language processing (NLP) called sentiment analysis, helping you learn how to use machine learning algorithms to classify documents.</p><p>This book is your companion to machine learning with Python, whether you're a Python developer new to machine learning or want to deepen your knowledge of the latest developments.</p><h4>What you will learn</h4><ul><li>Master the frameworks, models, and techniques that enable machines to 'learn' from data</li><li>Use scikit-learn for machine learning and TensorFlow for deep learning</li><li>Apply machine learning to image classification, sentiment analysis, intelligent web applications, and more</li><li>Build and train neural networks, GANs, and other models</li><li>Discover best practices for evaluating and tuning models</li><li>Predict continuous target outcomes using regression analysis</li><li>Dig deeper into textual and social media data using sentiment analysis</li></ul><h4>Who This Book Is For</h4><p>If you know some Python and you want to use machine learning and deep learning, pick up this book. Whether you want to start from scratch or extend your machine learning knowledge, this is an essential resource. Written for developers and data scientists who want to create practical machine learning and deep learning code, this book is ideal for anyone who wants to teach computers how to learn from data.</p>

Applied machine learning with a solid foundation in theory. Revised and expanded for TensorFlow 2, GANs, and reinforcement learning. Purchase of the print or Kindle book includes a free eBook in the PDF format.
Key Features Third edition of the bestselling, widely acclaimed Python machine learning book Clear and intuitive explanations take you deep into the theory and practice of Python machine learning Fully updated and expanded to cover TensorFlow 2, Generative Adversarial Network models, reinforcement learning, and best practices Book DescriptionPython Machine Learning, Third Edition is a comprehensive guide to machine learning and deep learning with Python. It acts as both a step-by-step tutorial, and a reference you'll keep coming back to as you build your machine learning systems. Packed with clear explanations, visualizations, and working examples, the book covers all the essential machine learning techniques in depth. While some books teach you only to follow instructions, with this machine learning book, Raschka and Mirjalili teach the principles behind machine learning, allowing you to build models and applications for yourself. Updated for TensorFlow 2.0, this new third edition introduces readers to its new Keras API features, as well as the latest additions to scikit-learn. It's also expanded to cover cutting-edge reinforcement learning techniques based on deep learning, as well as an introduction to GANs. Finally, this book also explores a subfield of natural language processing (NLP) called sentiment analysis, helping you learn how to use machine learning algorithms to classify documents. This book is your companion to machine learning with Python, whether you're a Python developer new to machine learning or want to deepen your knowledge of the latest developments.What you will learn Master the frameworks, models, and techniques that enable machines to learn from data Use scikit-learn for machine learning and TensorFlow for deep learning Apply machine learning to image classification, sentiment analysis, intelligent web applications, and more Build and train neural networks, GANs, and other models Discover best practices for evaluating and tuning models Predict continuous target outcomes using regression analysis Dig deeper into textual and social media data using sentiment analysis Who this book is for If you know some Python and you want to use machine learning and deep learning, pick up this book. Whether you want to start from scratch or extend your machine learning knowledge, this is an essential resource. Written for developers and data scientists who want to create practical machine learning and deep learning code, this book is ideal for anyone who wants to teach computers how to learn from data.
]]>

Explore the principles and practicalities of quantum computing Key Features Discover how quantum computing works and delve into the math behind it with this quantum computing textbook Learn how it may become the most important new computer technology of the century Explore the inner workings of quantum computing technology to quickly process complex cloud data and solve problems Book Description Quantum computing is making us change the way we think about computers. Quantum bits, a.k.a. qubits, can make it possible to solve problems that would otherwise be intractable with current computing technology. Dancing with Qubits is a quantum computing textbook that starts with an overview of why quantum computing is so different from classical computing and describes several industry use cases where it can have a major impact. From there it moves on to a fuller description of classical computing and the mathematical underpinnings necessary to understand such concepts as superposition, entanglement, and interference. Next up is circuits and algorithms, both basic and more sophisticated. It then nicely moves on to provide a survey of the physics and engineering ideas behind how quantum computing hardware is built. Finally, the book looks to the future and gives you guidance on understanding how further developments will affect you. Really understanding quantum computing requires a lot of math, and this book doesn't shy away from the necessary math concepts you'll need. Each topic is introduced and explained thoroughly, in clear English with helpful examples. What you will learn See how quantum computing works, delve into the math behind it, what makes it different, and why it is so powerful with this quantum computing textbook Discover the complex, mind-bending mechanics that underpin quantum systems Understand the necessary concepts behind classical and quantum computing Refresh and extend your grasp of essential mathematics, computing, and quantum theory Explore the main applications of quantum computing to the fields of scientific computing, AI, and elsewhere Examine a detailed overview of qubits, quantum circuits, and quantum algorithm Who this book is for Dancing with Qubits is a quantum computing textbook for those who want to deeply explore the inner workings of quantum computing. This entails some sophisticated mathematical exposition and is therefore best suited for those with a healthy interest in mathematics, physics, engineering, and comput..

Explore the principles and practicalities of quantum computingKey FeaturesDiscover how quantum computing works and delve into the math behind it with this quantum computing textbookLearn how it may become the most important new computer technology of the centuryExplore the inner workings of quantum computing technology to quickly process complex cloud data and solve problemsBook DescriptionQuantum computing is making us change the way we think about computers. Quantum bits, a.k.a. qubits, can make it possible to solve problems that would otherwise be intractable with current computing technology. Dancing with Qubits is a quantum computing textbook that starts with an overview of why quantum computing is so different from classical computing and describes several industry use cases where it can have a major impact. From there it moves on to a fuller description of classical computing and the mathematical underpinnings necessary to understand such concepts as superposition, entanglement, and interference. Next up is circuits and algorithms, both basic and more sophisticated. It then nicely moves on to provide a survey of the physics and engineering ideas behind how quantum computing hardware is built. Finally, the book looks to the future and gives you guidance on understanding how further developments will affect you. Really understanding quantum computing requires a lot of math, and this book doesn't shy away from the necessary math concepts you'll need. Each topic is introduced and explained thoroughly, in clear English with helpful examples.What you will learnSee how quantum computing works, delve into the math behind it, what makes it different, and why it is so powerful with this quantum computing textbookDiscover the complex, mind-bending mechanics that underpin quantum systemsUnderstand the necessary concepts behind classical and quantum computingRefresh and extend your grasp of essential mathematics, computing, and quantum theoryExplore the main applications of quantum computing to the fields of scientific computing, AI, and elsewhereExamine a detailed overview of qubits, quantum circuits, and quantum algorithmWho this book is forDancing with Qubits is a quantum computing textbook for those who want to deeply explore the inner workings of quantum computing. This entails some sophisticated mathematical exposition and is therefore best suited for those with a healthy interest in mathematics, physics, engineering, and computer science.

Unlock the power of artificial intelligence with top Udemy AI instructor Hadelin de Ponteves. Key Features Learn from friendly, plain English explanations and practical activities Put ideas into action with 5 hands-on projects that show step-by-step how to build intelligent software Use AI to win classic video games and construct a virtual self-driving car Book Description Welcome to the Robot World ... and start building intelligent software now! Through his best-selling video courses, Hadelin de Ponteves has taught hundreds of thousands of people to write AI software. Now, for the first time, his hands-on, energetic approach is available as a book. Starting with the basics before easing you into more complicated formulas and notation, AI Crash Course gives you everything you need to build AI systems with reinforcement learning and deep learning. Five full working projects put the ideas into action, showing step-by-step how to build intelligent software using the best and easiest tools for AI programming, including Python, TensorFlow, Keras, and PyTorch. AI Crash Course teaches everyone to build an AI to work in their applications. Once you've read this book, you're only limited by your imagination. What you will learn Master the basics of AI without any previous experience Build fun projects, including a virtual-self-driving car and a robot warehouse worker Use AI to solve real-world business problems Learn how to code in Python Discover the 5 principles of reinforcement learning Create your own AI toolkit Who this book is for If you want to add AI to your skillset, this book is for you. It doesn't require data science or machine learning knowledge. Just maths basics (high school level)

Link to the GitHub Repository containing the code examples and additional material:(https://github.com/rasbt/python-machine-learning-book) https://github.com/rasbt/python-machi...
Many of the most innovative breakthroughs and exciting new technologies can be attributed to applications of machine learning. We are living in an age where data comes in abundance, and thanks to the self-learning algorithms from the field of machine learning, we can turn this data into knowledge. Automated speech recognition on our smart phones, web search engines, e-mail spam filters, the recommendation systems of our favorite movie streaming services – machine learning makes it all possible.
Thanks to the many powerful open-source libraries that have been developed in recent years, machine learning is now right at our fingertips. Python provides the perfect environment to build machine learning systems productively.
This book will teach you the fundamentals of machine learning and how to utilize these in real-world applications using Python. Step-by-step, you will expand your skill set with the best practices for transforming raw data into useful information, developing learning algorithms efficiently, and evaluating results.
You will discover the different problem categories that machine learning can solve and explore how to classify objects, predict continuous outcomes with regression analysis, and find hidden structures in data via clustering. You will build your own machine learning system for sentiment analysis and finally, learn how to embed your model into a web app to share with the world

Machine learning and predictive analytics are transforming the way businesses and other organizations operate. Being able to understand trends and patterns in complex data is critical to success, becoming one of the key strategies for unlocking growth in a challenging contemporary marketplace. Python can help you deliver key insights into your data -- its unique capabilities as a language let you build sophisticated algorithms and statistical models that can reveal new perspectives and answer key questions that are vital for success. Python Machine Learning gives you access to the world of predictive analytics and demonstrates why Python is one of the world's leading data science languages. If you want to ask better questions of data, or need to improve and extend the capabilities of your machine learning systems, this practical data science book is invaluable. Covering a wide range of powerful Python libraries, including scikit-learn, Theano, and Pylearn2, and featuring guidance and tips on everything from sentiment analysis to neural networks, you'll soon be able to answer some of the most important questions facing you and your organization.

"Python Machine Learning, Third Edition" is a comprehensive guide to machine learning and deep learning with Python. It acts as both a clear step-by-step tutorial and a reference you'll keep coming back to as you build your machine learning systems. Packed with clear explanations, visualizations, and working examples, the book covers all the essential machine learning techniques in depth. While some books teach you only to follow instructions, Raschka and Mirjalili teach the principles behind machine learning, allowing you to build models and applications for yourself. This new third edition is updated for TensorFlow 2 and the latest additions to scikit-learn. It's expanded to cover two cutting-edge machine learning techniques: reinforcement learning and generative adversarial networks (GANs). -- From the rear cover

2020-11-29