Convolutional Neural Networks (CNN) for Image Recognition

4 hours of instruction

This course starts of a series of topics on neural networks designed to solve a particular family of tasks. In this course students will be able to get an overview of how to work with image data and build Convolutional Neural Networks (CNNs) – the industry standard for tackling image-based data.

OBJECTIVES

1. Define use cases for image analysis
2. Define the concept of a CNN and implement the CNN on the MNIST dataset

PREREQUISITES

Neural Networks & Deep Learning

SYLLABUS & TOPICS COVERED

1. Image Analysis With CNNs
   • Overview of CNNs and their use cases
   • Model inputs and outputs for image analysis type problems
2. CNN Architecture
   • CNN architecture
   • Training process of a CNN
3. CNN Implementation
   • Image data processing for CNNs
   • Building and implementing simple CNNs
   • Measuring and assessing performance

SOFTWARE REQUIREMENTS

You will have access to a Python-based JupyterHub environment for this course. No additional download or installation is required.