Learn the fundamentals of neural networks and how to build deep learning models using TensorFlow.
By continuing you accept the Terms of Use and Privacy Policy, that your data will be stored outside of the EU, and that you are 16 years or older.
Not long ago, cutting edge computer vision algorithms couldnâ€™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 2.0 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 house prices, credit card borrower defaults, and images of sign-language gestures.
What is graph-based computation? In this chapter, you'll learn about the engine that powers TensorFlow and what makes it such an attractive choice for data science projects. We will talk about constants and variables, basic operations, such as addition and multiplication, and advanced operations, such as differentiation. By the end of the chapter, you'll know how to construct and solve graph-based computational models.
In this chapter, you'll learn how to predict credit card default using neural networks defined and trained in TensorFlow. You will 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.
Here, you'll use TensorFlow to create a linear model that can predict house prices. You will start by learning how to load and manipulate data in TensorFlow. You'll then learn how to construct loss functions and minimize them to find the optimal parameter values for a linear model. Finally, you'll learn how to reduce the resource constraints of your program by using batch training.
In the final chapter, you'll use high-level APIs in TensorFlow to train a sign language letter classifier. You will use both the sequential and functional Keras APIs to train, validate, 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.
What is graph-based computation? In this chapter, you'll learn about the engine that powers TensorFlow and what makes it such an attractive choice for data science projects. We will talk about constants and variables, basic operations, such as addition and multiplication, and advanced operations, such as differentiation. By the end of the chapter, you'll know how to construct and solve graph-based computational models.
Here, you'll use TensorFlow to create a linear model that can predict house prices. You will start by learning how to load and manipulate data in TensorFlow. You'll then learn how to construct loss functions and minimize them to find the optimal parameter values for a linear model. Finally, you'll learn how to reduce the resource constraints of your program by using batch training.
In this chapter, you'll learn how to predict credit card default using neural networks defined and trained in TensorFlow. You will 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.
In the final chapter, you'll use high-level APIs in TensorFlow to train a sign language letter classifier. You will use both the sequential and functional Keras APIs to train, validate, 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.
â€śI've used other sites, but DataCamp's been the one that I've stuck with.â€ť
Devon Edwards Joseph
Lloyd's Banking Group
â€śDataCamp is the top resource I recommend for learning data science.â€ť
Louis Maiden
Harvard Business School
â€śDataCamp is by far my favorite website to learn from.â€ť
Ronald Bowers
Decision Science Analytics @ USAA