Skip to main content

Introducing new learning courses and educational videos from Apress. Start watching

  • Book
  • © 2018

Applied Deep Learning

A Case-Based Approach to Understanding Deep Neural Networks

Apress
  • Contains a complete overview of regularization, learning rate decay techniques, and different optimizers such as Adam or RMSProp with complete examples implemented in Python and TensorFlow. The mathematical background is studied in detail

  • Implements advanced techniques such as dropout and hyper-parameter tuning in Python and TensorFlow

  • Contains an overview of the building blocks of convolutional and recurrent neural networks

Buying options

eBook USD 54.99
Price excludes VAT (USA)
  • ISBN: 978-1-4842-3790-8
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout

This is a preview of subscription content, access via your institution.

Table of contents (10 chapters)

  1. Front Matter

    Pages i-xxi
  2. Computational Graphs and TensorFlow

    • Umberto Michelucci
    Pages 1-29
  3. Single Neuron

    • Umberto Michelucci
    Pages 31-81
  4. Feedforward Neural Networks

    • Umberto Michelucci
    Pages 83-136
  5. Training Neural Networks

    • Umberto Michelucci
    Pages 137-184
  6. Regularization

    • Umberto Michelucci
    Pages 185-216
  7. Metric Analysis

    • Umberto Michelucci
    Pages 217-270
  8. Hyperparameter Tuning

    • Umberto Michelucci
    Pages 271-322
  9. Convolutional and Recurrent Neural Networks

    • Umberto Michelucci
    Pages 323-364
  10. A Research Project

    • Umberto Michelucci
    Pages 365-389
  11. Logistic Regression from Scratch

    • Umberto Michelucci
    Pages 391-401
  12. Back Matter

    Pages 403-410

About this book

Work with advanced topics in deep learning, such as optimization algorithms, hyper-parameter tuning, dropout, and error analysis as well as strategies to address typical problems encountered when training deep neural networks. You’ll begin by studying the activation functions mostly with a single neuron (ReLu, sigmoid, and Swish), seeing how to perform linear and logistic regression using TensorFlow, and choosing the right cost function. 

The next section talks about more complicated neural network architectures with several layers and neurons and explores the problem of random initialization of weights. An entire chapter is dedicated to a complete overview of neural network error analysis, giving examples of solving problems originating from variance, bias, overfitting, and datasets coming from different distributions. 

Applied Deep Learning also discusses how to implement logistic regression completely from scratch without using any Python library except NumPy, to let you appreciate how libraries such as TensorFlow allow quick and efficient experiments. Case studies for each method are included to put into practice all theoretical information. You’ll discover tips and tricks for writing optimized Python code (for example vectorizing loops with NumPy). 

You will:

  • Implement advanced techniques in the right way in Python and TensorFlow
  • Debug and optimize advanced methods (such as dropout and regularization)
  • Carry out error analysis (to realize if one has a bias problem, a variance problem, a data offset problem, and so on)
  • Set up a machine learning project focused on deep learning on a complex dataset

Keywords

  • Deep Learning
  • TensorFlow
  • Skilearn
  • Regularization
  • Dropout
  • Convolutional Neural Networks
  • Recursive Neural Networks
  • Neuron Activation Functions
  • Python

Authors and Affiliations

  • toelt.ai, Dübendorf, Switzerland

    Umberto Michelucci

About the author

Umberto is currently the head of Innovation in BI & Analytics at a leading health insurance company in Switzerland, where he leads several strategic initiatives that deal with AI, new technologies and machine learning. He worked as data scientist and lead modeller in several big projects in healthcare and has extensive hands-on experience in programming and designing algorithms. Before that he managed projects in BI and DWH enabling data driven solutions to be implemented in complicated productive environments. He worked extensively with neural networks the last two years and applied deep learning to several problems linked to insurance and client behaviour (like customer churning). He presented his results on deep learning at international conferences and internally gained a reputation for his huge experience with Python and deep learning. 

Bibliographic Information

Buying options

eBook USD 54.99
Price excludes VAT (USA)
  • ISBN: 978-1-4842-3790-8
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout