In this chapter, you will learn how to implement your first neural network using Keras. This chapter covers the basics of deep learning and will provide you with the foundation necessary to build highly complex neural network architectures. We start by extending the logistic regression model to a simple single-layer neural network and then proceed to more complicated neural networks with multiple hidden layers. In this process, you will learn about the underlying basic concepts of neural networks, including forward propagation for making predictions, computing loss, backpropagation for computing derivative of loss with respect to model parameters, and finally gradient descent for learning optimal parameters for the model. You will also learn about the various choices available to build and train a neural network in terms of activation functions, loss functions, and optimizers.
Furthermore, you will learn how to evaluate your model while understanding issues such as overfitting...
In this section, you will first learn about the representations and concepts of deep learning such as forward propagation, backpropagation, and gradient descent. We will not delve deeply into these concepts, as it isn't required for this book. However, the coverage will essentially help anyone who wants to apply deep learning to a problem.
We then will move on to implementing neural networks using Keras. Also, we will stick to the simplest case, which is a neural network with a single hidden layer. You will learn how to define a model in Keras, choose the hyperparameters, and then train your model. At the end of this section, you will have the opportunity to practice what you have learned by implementing a neural network in Keras to perform classification on a dataset and observe how neural networks outperform simpler models such as logistic regression.
In this section, we will move on to multi-layer or deep neural networks while learning about techniques for assessing the performance of a model. As you may have already realized, there are many hyperparameter choices to be made when building a deep neural network. Some very important challenges of applied deep learning are how to find the right values for the number of hidden layers, the number of units in each hidden layer, the type of activation function to use for each layer, the type of optimizer and loss function for training the network, among others. Model evaluation is required for making these decisions. By performing model evaluation, you can say whether a specific deep architecture or a specific set of hyperparameters is working poorly or well on a particular dataset, and therefore decide whether to change them or not.
Furthermore, you will learn about overfitting and underfitting in this section. These are two very important issues that can arise when building...
In this chapter, you learned about the basics of deep learning, including the common representations and terminology and essential underlying concepts. You learned how forward propagation in neural networks works and how it is used for predicting outputs. You learned about the loss function as a measure of model performance and learned how backpropagation is used to compute the derivatives of loss function with respect to model parameters. Finally, you learned about gradient descent, which uses the gradients computed by backpropagation to gradually update the model parameters. In addition to basic theory and concepts, you also learned how to implement and train shallow and deep neural networks with Keras and how to use a trained network to make predictions about the output of a given input. You also learned how to evaluate the overall performance of the network over all data examples, and the reasons why evaluating a model on training examples can be misleading. You learned about...
© 2019 Packt Publishing Limited All Rights ReservedAuthors (3)
