• Course Introduction
• Compare AI vs ML vs DL
• Understanding how machines learn
• Structured vs. Unstructured data

Lab:

• Installing Anaconda and TensorFlow
• Introduction to neural networks
  • The math behind neural networks
  • Activation functions
  • Vanishing gradient problem and ReLU
  • Loss functions
  • Gradient descent
  • Back propagation
• Understanding the intuition behind neural networks
• Introducing Perceptrons
  • Single Layer linear classifier
  • Step Function
  • Updating the weights
  • Linear separability and XOR problem
• Hidden Layers: Intro to Deep Neural Networks
• Introducing Keras/TensorFlow
  • TensorFlow intro
  • What is Keras?

Lab:

• Using Keras to implement a neural network
• Understanding Images
• Images as visual data

Lab:

• Building a DNN model for image classification
• Deep Learning
• The architecture of deep learning
• The advantages of deep learning
• Convolutional Neural Networks
• Convolutions
  • Size
  • Stride
  • Padding
• Pooling
• Fully-connected layer
• Dropout Layer
• Understanding Google Cloud Platform

Lab:

• Getting Started with GCP
• Using GCP for Deep Learning
• Project creation
• Cloud storage
• Introducing AI Platform
• AI Platform Notebooks
• TensorFlow
• AI Hub

Lab:

• Creating a TensorFlow model using AI Platform Notebooks

Lab:

• Building a Convolutional Neural Network
• Pre-built ML Models for Image Classification on GCP
• Understanding pre-built models
• Cloud Vision API
• GCP Deep Learning Project

Lab Project:

• Creating an Image Classifier with a CNN
• Next steps

• Installing Anaconda and TensorFlow
• Using Keras to implement a neural network
• Building a DNN model for image classification
• Getting Started with GCP
• Creating a TensorFlow model using AI Platform
• Notebooks
• Building a Convolutional Neural Network
• Creating an Image Classifier with a CNN