Loved by learners at thousands of companies
Not long ago, cutting-edge computer vision algorithms couldn’t differentiate between images of cats and dogs. Today, a skilled data scientist equipped with nothing more than a laptop can classify tens of thousands of objects with greater accuracy than the human eye. In this course, you will use TensorFlow 2.6 to develop, train, and make predictions with the models that have powered major advances in recommendation systems, image classification, and FinTech. You will learn both high-level APIs, which will enable you to design and train deep learning models in 15 lines of code, and low-level APIs, which will allow you to move beyond off-the-shelf routines. You will also learn to accurately predict housing prices, credit card borrower defaults, and images of sign language gestures.
Introduction to TensorFlowFree
Before you can build advanced models in TensorFlow 2, you will first need to understand the basics. In this chapter, you’ll learn how to define constants and variables, perform tensor addition and multiplication, and compute derivatives. Knowledge of linear algebra will be helpful, but not necessary.Constants and variables50 xpDefining data as constants100 xpDefining variables100 xpBasic operations50 xpPerforming element-wise multiplication100 xpMaking predictions with matrix multiplication100 xpSumming over tensor dimensions50 xpAdvanced operations50 xpReshaping tensors100 xpOptimizing with gradients100 xpWorking with image data100 xp
In this chapter, you will learn how to build, solve, and make predictions with models in TensorFlow 2. You will focus on a simple class of models – the linear regression model – and will try to predict housing prices. By the end of the chapter, you will know how to load and manipulate data, construct loss functions, perform minimization, make predictions, and reduce resource use with batch training.Input data50 xpLoad data using pandas100 xpSetting the data type100 xpLoss functions50 xpLoss functions in TensorFlow100 xpModifying the loss function100 xpLinear regression50 xpSet up a linear regression100 xpTrain a linear model100 xpMultiple linear regression100 xpBatch training50 xpPreparing to batch train100 xpTraining a linear model in batches100 xp
The previous chapters taught you how to build models in TensorFlow 2. In this chapter, you will apply those same tools to build, train, and make predictions with neural networks. You will learn how to define dense layers, apply activation functions, select an optimizer, and apply regularization to reduce overfitting. You will take advantage of TensorFlow's flexibility by using both low-level linear algebra and high-level Keras API operations to define and train models.Dense layers50 xpThe linear algebra of dense layers100 xpThe low-level approach with multiple examples100 xpUsing the dense layer operation100 xpActivation functions50 xpBinary classification problems100 xpMulticlass classification problems100 xpOptimizers50 xpThe dangers of local minima100 xpAvoiding local minima100 xpTraining a network in TensorFlow50 xpInitialization in TensorFlow100 xpDefining the model and loss function100 xpTraining neural networks with TensorFlow100 xp
High Level APIs
In the final chapter, you'll use high-level APIs in TensorFlow 2 to train a sign language letter classifier. You will use both the sequential and functional Keras APIs to train, validate, make predictions with, and evaluate models. You will also learn how to use the Estimators API to streamline the model definition and training process, and to avoid errors.Defining neural networks with Keras50 xpThe sequential model in Keras100 xpCompiling a sequential model100 xpDefining a multiple input model100 xpTraining and validation with Keras50 xpTraining with Keras100 xpMetrics and validation with Keras100 xpOverfitting detection100 xpEvaluating models100 xpTraining models with the Estimators API50 xpPreparing to train with Estimators100 xpDefining Estimators100 xpCongratulations!50 xp
PrerequisitesSupervised Learning with scikit-learn
Isaiah Hull is a visiting associate professor of finance at BI Norwegian Business School and the author of Machine Learning for Economics and Finance in TensorFlow 2. He holds a PhD in economics from Boston College and conducts research on computational economics, machine learning, and quantum computing.