TensorFlow Machine Learning Projects is for you if you are a data analyst, data scientist, machine learning professional, or deep learning enthusiast with a basic knowledge of TensorFlow. This book is also for you if you want to build end-to-end projects in the machine learning domain using supervised, unsupervised, and reinforcement learning techniques.

Chapter 1, Overview of TensorFlow and Machine Learning, explains the basics of TensorFlow and has you build a machine learning model using logistic regression to classify hand-written digits.

Chapter 2, Using Machine Learning to Detect Exoplanets in Outer Space, covers how to detect exoplanets in outer space using ensemble methods that are based on decision trees.

Chapter 3, Sentiment Analysis in Your Browser Using TensorFlow.js, explains how to train and build a model on your web browser using TensorFlow.js. We will build a sentiment analysis model using a movie reviews dataset and deploy it to your web browser for making predictions.

Chapter 4, Digit Classification Using TensorFlow Lite, focuses on building a deep learning model for classifying hand-written digits and converting them into a mobile-friendly format using TensorFlow Lite. We will also learn about the architecture of TensorFlow Lite and how to use TensorBoard for visualizing neural networks.

Chapter 5, Speech to Text and Topic Extraction Using NLP, focuses on learning about various options for speech-to-text and pre-built models by Google in TensorFlow using the Google Speech Command dataset.

Chapter 6, Predicting Stock Prices using Gaussian Process Regression, explains a popular forecasting model called a Gaussian process in Bayesian statistics. We use Gaussian processes from a GpFlow library built on top of TensorFlow to develop a stock price prediction model. 

Chapter 7, Credit Card Fraud Detection Using Autoencoders, introduces a dimensionality reduction technique called autoencoders. We identify fraudulent transactions in a credit card dataset by building autoencoders using TensorFlow and Keras.

Chapter 8, Generating Uncertainty in Traffic Signs Classifier using Bayesian Neural Networks, explains Bayesian neural networks, which help us to quantify the uncertainty in predictions. We will build a Bayesian neural network using TensorFlow to classify German traffic signs. 

Chapter 9, Generating Matching Shoe Bags from Shoe Images Using DiscoGANs, introduces a new type of GAN known as Discovery GANs (DiscoGANs). We understand how its architecture differs from standard GANs and how it can be used in style transfer problems. Finally, we build a DiscoGAN model in TensorFlow to generate matching shoe bags from shoe images, and vice versa.

Chapter 10, Classifying Clothing Images Using Capsule Networks, implements a very recent image classification model—Capsule Networks. We get to understand its architecture and explain the nuances of its implementation in TensorFlow. We use the Fashion MNIST dataset to classify clothing images using this model.

Chapter 11, Making Quality Product Recommendations Using TensorFlow, covers techniques such as matrix factorization (SVD++), learning to rank, and convolutional neural network variations for recommendation tasks with TensorFlow.

Chapter 12, Object Detection at a Large Scale with TensorFlow, explores Yahoo's TensorFlowOnSpark framework for distributed deep learning on Spark clusters. Then, we will apply TensorFlowOnSpark to a large-scale dataset of images and train the network to detect objects. 

Chapter 13, Generating Book Scripts Using LSTMs, explains how LSTMs are useful in generating new text. We use a book script from one of Packt's published books to bsuild an LSTM-based deep learning model that can generate book scripts on its own. 

Chapter 14, Playing Pacman Using Deep Reinforcement Learning, explains the utilization of reinforcement learning for training a model to play Pacman, teaching you about reinforcement learning in the process.

Chapter 15, What is Next?, introduces the other components of the TensorFlow ecosystem that are useful for deploying the models in production. We will also learn about various applications of AI across industries, the limitations of deep learning, and ethics in AI.

To get the most out of this book, download the book code from the GitHub repository and practice with the code in Jupyter Notebooks. Also, practice modifying the implementations already provided by the authors. 

tf.constant(
  value,
  dtype=None,
  shape=None,
  name='const_name',
  verify_shape=False
  )

const1 (x):  Tensor("x:0", shape=(), dtype=int32)
const2 (y):  Tensor("y:0", shape=(), dtype=float32)
const3 (z):  Tensor("z:0", shape=(), dtype=float16)

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.