Book Image

Hands-On Deep Learning with TensorFlow

By : Dan Van Boxel
Book Image

Hands-On Deep Learning with TensorFlow

By: Dan Van Boxel

Overview of this book

Dan Van Boxel’s Deep Learning with TensorFlow is based on Dan’s best-selling TensorFlow video course. With deep learning going mainstream, making sense of data and getting accurate results using deep networks is possible. Dan Van Boxel will be your guide to exploring the possibilities with deep learning; he will enable you to understand data like never before. With the efficiency and simplicity of TensorFlow, you will be able to process your data and gain insights that will change how you look at data. With Dan’s guidance, you will dig deeper into the hidden layers of abstraction using raw data. Dan then shows you various complex algorithms for deep learning and various examples that use these deep neural networks. You will also learn how to train your machine to craft new features to make sense of deeper layers of data. In this book, Dan shares his knowledge across topics such as logistic regression, convolutional neural networks, recurrent neural networks, training deep networks, and high level interfaces. With the help of novel practical examples, you will become an ace at advanced multilayer networks, image recognition, and beyond.
Table of Contents (12 chapters)

Index

A

  • activation functions / Sigmoid function

B

  • backpropagation / Backpropagation
  • basic neural networks
    • about / Basic neural networks
    • log function / Log function
    • sigmoid function / Sigmoid function

C

  • CoCalc
    • TensorFlow, installing via / Installing via CoCalc
    • reference / Installing via CoCalc
  • computations
    • defining / Simple computations
    • scalars, defining / Defining scalars and tensors
    • tensors, defining / Defining scalars and tensors
    • on tensors / Computations on tensors
    • performing / Doing computation
    • intermediate values, viewing / Viewing and substituting intermediate values
    • intermediate values, submitting / Viewing and substituting intermediate values
  • convolutional and pooling layer combo
    • adding / Adding convolutional and pooling layer combo
  • convolutional layer
    • about / Convolutional layer motivation
    • multiple features, extracting / Multiple features extracted
  • convolutional layer application
    • implementing / Convolutional layer application
    • about / Exploring the convolution layer
  • convolutional neural network
    • about / Convolutional neural network
  • Convolutional Neural Network (CNN)
    • fonts, classifying / CNN to classify our fonts
  • Convolutional Neural Networks (CNNs)
    • about / Convolutional Neural Networks (CNNs) in Learn

D

  • deep CNN
    • about / Deep CNN
    • convolutional and pooling layer combo, adding / Adding convolutional and pooling layer combo
  • deep convolutional neural network / Deep convolutional neural network
  • deeper CNN
    • layers, adding / Adding a layer to another layer of CNN
    • conclusion / Wrapping up deep CNN
  • deep neural network
    • about / The multiple hidden layer model, Deep neural network
  • Dense Neural Network (DNN)
    • about / DNNs
    • CNNs / Convolutional Neural Networks (CNNs) in Learn
    • weights, extracting / Extracting weights

E

  • epoch / Training the model

F

  • font classification dataset / Introducing the font classification dataset

H

  • hyper parameter optimization / Exploring the multiple hidden layer model

I

  • installation page, TensorFlow / TensorFlow – the installation page

J

  • Jupyter / Installing via CoCalc

K

  • Keras
    • URL / TensorFlow learn

L

  • log function / Log function
  • logistic regression / Logistic regression, Logistic regression
    • about / Logistic regression model building
    • implementing / Getting data ready
  • logistic regression model
    • weights, viewing of / Understanding weights of the model
    • about / The logistic regression model
  • logistic regression model building
    • about / Logistic regression model building
    • font classification dataset / Introducing the font classification dataset
  • logistic regression training
    • about / Logistic regression training
    • loss function, developing / Developing the loss function
    • model, training / Training the model
    • model accuracy, evaluating / Evaluating the model accuracy

M

  • main page, TensorFlow / TensorFlow – main page
  • models
    • about / A quick review of all the models
    • logistic regression model / The logistic regression model
    • single hidden layer neural network model / The single hidden layer neural network model
    • deep neural network / Deep neural network
    • convolutional neural network / Convolutional neural network
    • deep convolutional neural network / Deep convolutional neural network
  • multiple hidden layer model
    • about / The multiple hidden layer model
    • exploring / Exploring the multiple hidden layer model
    • results / Results of the multiple hidden layer
  • multiple hidden layers graph / Understanding the multiple hidden layers graph

N

  • neuron / Sigmoid function

P

  • pip
    • TensorFlow, installing via / Installing via pip
  • pooling layer application
    • about / Pooling layer application
  • pooling layers
    • about / Pooling layer motivation
    • max pooling layers / Max pooling layers

R

  • Recurrent Neural Networks (RNNs)
    • about / Exploring RNNs, Understanding RNNs
    • weights, modeling / Modeling the weights
    • using / Modeling the weights
  • research evaluation
    • about / Research evaluation

S

  • same padding
    • about / Convolutional layer motivation
  • scalars
    • defining / Defining scalars and tensors
  • sigmoid function / Sigmoid function
  • single hidden layer model
    • about / Single hidden layer model, Single hidden layer explained
    • exploring / Exploring the single hidden layer model
  • single hidden layer neural network model
    • about / The single hidden layer neural network model
  • Stochastic Gradient Descent (SGD)
    • about / DNNs

T

  • TensorFlow
    • installing / Installing TensorFlow
    • main page / TensorFlow – main page
    • installation page / TensorFlow – the installation page
    • installing, via pip / Installing via pip
    • installing, via CoCalc / Installing via CoCalc
    • future / The future of TensorFlow
    • projects / Some more TensorFlow projects
  • TensorFlow learn
    • about / TensorFlow learn
    • reference link / TensorFlow learn
    • setup / Setup
    • logistic regression / Logistic regression
  • TensorFlow model
    • building / Building a TensorFlow model
  • TensorFlow Slim
    • reference link / TensorFlow learn
  • tensors
    • defining / Defining scalars and tensors
    • computations on / Computations on tensors

V

  • variable tensors / Variable tensors

W

  • weights
    • modeling / Modeling the weights
    • extracting / Extracting weights
  • wheel file / TensorFlow – the installation page