Extending your deep learning education

Contents

• Introduction Introduction

  • Getting started with deep learning

    54s
  • Prerequisites for the course

    2m 18s
  • Setting up the environment

    2m 31s
• 1. Introduction to Deep Learning 1. Introduction to Deep Learning

  • What is deep learning?

    1m 33s
  • Linear regression

    2m 40s
  • An analogy for deep learning

    2m 45s
  • The perceptron

    1m 35s
  • Artificial neural networks

    2m 34s
  • Training an ANN

    2m 24s
• 2. Neural Network Architecture 2. Neural Network Architecture

  • The input layer

    2m 53s
  • Hidden layers

    1m 47s
  • Weights and biases

    2m 24s
  • Activation functions

    1m 56s
  • The output layer

    1m 26s
• 3. Training a Neural Network 3. Training a Neural Network

  • Setup and initialization

    2m 43s
  • Forward propagation

    1m 14s
  • Measuring accuracy and error

    2m 12s
  • Back propagation

    2m 8s
  • Gradient descent

    1m 21s
  • Batches and epochs

    2m 22s
  • Validation and testing

    1m 28s
  • An ANN model

    1m 39s
  • Reusing existing network architectures

    2m 33s
  • Using available open-source models

    2m 27s
• 4. Deep Learning Example 1 4. Deep Learning Example 1

  • The Iris classification problem

    1m 25s
  • Input preprocessing

    2m 37s
  • Creating a deep learning model

    2m 30s
  • Training and evaluation

    2m 45s
  • Saving and loading models

    1m 7s
  • Predictions with deep learning models

    1m 30s
• 5. Deep Learning Example 2 5. Deep Learning Example 2

  • Spam classification problem

    1m 40s
  • Creating text representations

    1m 58s
  • Building a spam model

    1m 27s
  • Predictions for text

    1m 22s
• 6. Deep Learning Exercise 6. Deep Learning Exercise

  • Exercise problem statement

    2m 21s
  • Preprocessing RCA data

    1m 6s
  • Building the RCA model

    50s
  • Predicting root causes with deep learning

    54s
• Conclusion Conclusion

  • Extending your deep learning education

    37s