官术网_书友最值得收藏!

Getting Started with Neural Networks

In this chapter, we will be focusing on the basics of neural networks, including input/output layers, hidden layers, and how the networks learn through forward and backpropagation. We will start with the standard multilayer perceptron networks, talk about their building blocks, and illustrate how they learn step-by-step. We will also introduce a few, popular standard models such as Convolutional Neural Networks (CNN), Restricted Boltzmann Machines (RBM), and recurrent neural network (RNN) as well as its variation Long Short-Term Memory (LSTM). We will outline the key, critical components for the successful application of the models, and explain some important concepts to help you gain a better understanding of why these networks work so well in certain areas. In addition to a theoretical introduction, we will also show example code snippets using TensorFlow on how to construct layers and activation functions, and how to connect different layers. In the end, we will demonstrate an end-to-end example of MNIST classification using TensorFlow. With the setup you learned from Chapter 2Getting Yourself Ready for Deep Learning it’s time we jump into some real examples to get our hands dirty.

The outline of this chapter is as follows:

  • Multilayer perceptrons:
    • The input layers
    • The output layers
    • Hidden layers
    • Activation functions
  • How a network learns
  • Deep learning models:
    • Convolutional Neural Networks
    • Restricted Boltzmann Machines
    • RNN/LSTM
  • MNIST hands-on classification example
主站蜘蛛池模板: 竹山县| 那坡县| 玉屏| 宾川县| 新郑市| 萨迦县| 安泽县| 英超| 双鸭山市| 南澳县| 茶陵县| 湾仔区| 台湾省| 永仁县| 成武县| 利川市| 怀宁县| 迁西县| 芮城县| 广宗县| 武定县| 浦城县| 云安县| 南昌市| 通化县| 神木县| 武宁县| 个旧市| 株洲市| 庆城县| 奉贤区| 当雄县| 承德县| 巩义市| 贵州省| 五常市| 弥渡县| 仙居县| 理塘县| 凤山市| 安福县|