This Learning Path is your complete guide to quickly getting to grips with popular machine learning algorithms. You'll be introduced to the most widely used algorithms in supervised, unsupervised, and semi-supervised machine learning, and learn how to use them in the best possible manner. Ranging from Bayesian models to the MCMC algorithm to Hidden Markov models, this Learning Path will teach you how to extract features from your dataset and perform dimensionality reduction by making use of Python-based libraries.
You'll bring the use of TensorFlow and Keras to build deep learning models, using concepts such as transfer learning, generative adversarial networks, and deep reinforcement learning. Next, you'll learn the advanced features of TensorFlow1.x, such as distributed TensorFlow with TF clusters, deploy production models with TensorFlow Serving. You'll implement different techniques related to object classification, object detection, image segmentation, and more.
By the end of this Learning Path, you'll have obtained in-depth knowledge of TensorFlow, making you the go-to person for solving artificial intelligence problems
This Learning Path includes content from the following Packt products:
- Mastering Machine Learning Algorithms by Giuseppe Bonaccorso
- Mastering TensorFlow 1.x by Armando Fandango
- Deep Learning for Computer Vision by Rajalingappaa Shanmugamani
This Learning Path is for data scientists, machine learning engineers, artificial intelligence engineers who want to delve into complex machine learning algorithms, calibrate models, and improve the predictions of the trained model. You will encounter the advanced intricacies and complex use cases of deep learning and AI. A basic knowledge of programming in Python and some understanding of machine learning concepts are required to get the best out of this Learning Path.
Chapter 1, Machine Learning Model Fundamentals, explains the most important theoretical concepts regarding machine learning models, including bias, variance, overfitting, underfitting, data normalization, and cost functions. It can be skipped by those readers with a strong knowledge of these concepts.
Chapter 2, Introduction to Semi-Supervised Learning, introduces the reader to the main elements of semi-supervised learning, focusing on inductive and transductive learning algorithms.
Chapter 3, Graph-Based Semi-Supervised Learning, continues the exploration of semisupervised learning algorithms belonging to the families of graph-based and manifold learning models. Label propagation and non-linear dimensionality reduction are analyzed in different contexts, providing some effective solutions that can be immediately exploited using Scikit-Learn functionalities.
Chapter 4, Bayesian Networks and Hidden Markov Models, introduces the concepts of probabilistic modeling using direct acyclic graphs, Markov chains, and sequential processes.
Chapter 5, EM Algorithm and Applications, explains the generic structure of the Expectation-Maximization (EM) algorithm. We discuss some common applications, such as Gaussian mixture, Principal Component Analysis, Factor Analysis, and Independent Component Analysis. This chapter requires deep mathematical knowledge; however, the reader can skip the proofs and concentrate on the final results.
Chapter 6, Hebbian Learning and Self-Organizing Maps, introduces Hebb's rule, which is one of the oldest neuro-scientific concepts and whose applications are incredibly powerful. The chapter explains how a single neuron works and presents two complex models (Sanger network and Rubner-Tavan network) that can perform a Principal Component Analysis without the input covariance matrix.
Chapter 7, Clustering Algorithms, introduces some common and important unsupervised algorithms, such as k-Nearest Neighbors (based on KD Trees and Ball Trees), K-means (with K-means++ initialization), fuzzy C-means, and spectral clustering. Some important metrics (such as Silhouette score/plots) are also analyzed.
Chapter 8, Advanced Neural Models, continues the explanation of the most important deep learning methods focusing on convolutional networks, recurrent networks, LSTM, and GRU.
Chapter 9, Classical Machine Learning with TensorFlow, teaches us to use TensorFlow to implement classical machine learning algorithms, such as linear regression and classification with logistic regression.
Chapter 10, Neural Networks and MLP with TensorFlow and Keras, introduces the concept of neural networks and shows how to build simple neural network models. We also cover how to build deep neural network models known as MultiLayer Perceptrons.
Chapter 11, RNN with TensorFlow and Keras, covers how to build Recurrent Neural Networks with TensorFlow and Keras. We cover the internal architecture of RNN, Long Short-Term Networks (LSTM), and Gated Recurrent Units (GRU). We provide a brief overview of the API functions and classes provided by TensorFlow and Keras to implement RNN models.
Chapter 12, CNN with TensorFlow and Keras, covers CNN models for image data and provides examples in TensorFlow and Keras libraries. We implement the LeNet architecture pattern for our example.
Chapter 13, Autoencoder with TensorFlow and Keras, illustrates the Autoencoder models for image data and again provides examples in TensorFlow and Keras libraries. We show the implementation of Simple Autoencoder, Denoising Autoencoder, and Variational Autoencoders.
Chapter 14, TensorFlow Models in Production with TF Serving, teaches us to deploy the models with TensorFlow Serving. We learn how to deploy using TF Serving in Docker containers and Kubernetes clusters.
Chapter 15, Deep Reinforcement Learning, covers reinforcement learning and the OpenAI gym. We build and train several models using various reinforcement learning strategies, including deep Q networks.
Chapter 16, Generative Adversarial Networks, shows how to build and train generative adversarial models in TensorFLow and Keras. We provide examples of SimpleGAN and DCGAN.
Chapter 17, Distributed Models with TensorFlow Clusters, covers distributed training for TensorFLow models using TensorFLow clusters. We provide examples of asynchronous and synchronous update methods for training models in data-parallel fashion.
Chapter 18, Debugging TensorFlow Models, tells us strategies and techniques to find problem hotspots when the models do not work as expected. We cover TensorFlow debugger, along with other methods.
Chapter 19, Tensor Processing Units, gives a brief overview of Tensor Processing Units. TPUs are futuristic platforms optimized to train and run TensorFlow models. Although not widely available yet, they are available on the Google Cloud Platform and slated to be available soon outside the GCP.
Chapter 20, Getting Started with Deep Learning, introduces the basics of deep learning and makes the readers familiar with the vocabulary. The readers will install the software packages necessary to follow the rest of the chapters.
Chapter 21, Image Classification, talks about the image classification problem, which is labeling an image as a whole. The readers will learn about image classification techniques and train a deep learning model for pet classification. They will also learn methods to improve accuracy and dive deep into variously advanced architectures.
Chapter 22, Image Retrieval, covers deep features and image retrieval. The reader will learn about various methods of obtaining model visualization, visual features, inference using TensorFlow, and serving and using visual features for product retrieval.
Chapter 23, Object Detection, talks about detecting objects in images. The reader will learn about various techniques of object detection and apply them for pedestrian detection. The TensorFlow API for object detection will be utilized in this chapter.
Chapter 24, Semantic Segmentation, covers segmenting of images pixel-wise. The readers will earn about segmentation techniques and train a model for segmentation of medical images.
Chapter 25, Similarity Learning, talks about similarity learning. The readers will learn about similarity matching and how to train models for face recognition. A model to train facial landmark is illustrated.
It's important to have basic-intermediate Python knowledge with a specific focus on NumPy.All the examples are based on Python 3.5+. It is suggested to use the Anaconda distribution (https://www.anaconda.com/download/ ), which is probably the most complete and powerful one for scientific projects. A good mathematics background is necessary to fully understand the theoretical part. In particular, basic skills in probability theory, calculus, and linear algebra are required.
To practice the TensorFlow chapter, you will need Docker and Kubernetes installed. It's preferable that the reader has GPU hardware but it's not necessary.
You can download the example code files for this book from your account at www.packt.com. If you purchased this book elsewhere, you can visit www.packt.com/support and register to have the files emailed directly to you.
You can download the code files by following these steps:
- Log in or register at www.packt.com.
- Select the
SUPPORTtab. - Click on
Code Downloads & Errata. - Enter the name of the book in the
Searchbox and follow the onscreen instructions.
Once the file is downloaded, please make sure that you unzip or extract the folder using the latest version of:
- WinRAR/7-Zip for Windows
- Zipeg/iZip/UnRarX for Mac
- 7-Zip/PeaZip for Linux
The code bundle for the book is also hosted on GitHub at https://github.com/PacktPublishing/Python-Advanced-Guide-to-Artificial-Intelligence. In case there's an update to the code, it will be updated on the existing GitHub repository.
We also have other code bundles from our rich catalog of books and videos available at https://github.com/PacktPublishing/. Check them out!
There are a number of text conventions used throughout this book.
CodeInText: Indicates code words in text, database table names, folder names, filenames, file extensions, pathnames, dummy URLs, user input, and Twitter handles. Here is an example: "As the optimization algorithm requires a single array, we have stacked all vectors into a horizontal array theta0 using the np.hstack() function."
A block of code is set as follows:
from sklearn.model_selection import train_test_split X_train, X_test, Y_train, Y_test = train_test_split(X, Y, train_size=0.7, random_state=1)
Any command-line input or output is written as follows:
graph = tf.get_default_graph()Bold: Indicates a new term, an important word, or words that you see onscreen. For example, words in menus or dialog boxes appear in the text like this. Here is an example: "If you need something different, click on the DOWNLOADS link in the header for all possible downloads:"
Feedback from our readers is always welcome.
General feedback: If you have questions about any aspect of this book, mention the book title in the subject of your message and email us at [email protected].
Errata: Although we have taken every care to ensure the accuracy of our content, mistakes do happen. If you have found a mistake in this book, we would be grateful if you would report this to us. Please visit www.packt.com/submit-errata, selecting your book, clicking on the Errata Submission Form link, and entering the details.
Piracy: If you come across any illegal copies of our works in any form on the Internet, we would be grateful if you would provide us with the location address or website name. Please contact us at [email protected] with a link to the material.
If you are interested in becoming an author: If there is a topic that you have expertise in and you are interested in either writing or contributing to a book, please visit authors.packtpub.com.
Please leave a review. Once you have read and used this book, why not leave a review on the site that you purchased it from? Potential readers can then see and use your unbiased opinion to make purchase decisions, we at Packt can understand what you think about our products, and our authors can see your feedback on their book. Thank you!
For more information about Packt, please visit packt.com.