• Online, Self-Paced
Course Description

Explore how to perform dimensionality reduction using powerful unsupervised learning techniques such as Principal Components Analysis and autoencoding.

Learning Objectives

TensorFlow: Building Autoencoders in TensorFlow

  • Course Overview
  • recognize how patterns help encode data
  • define how autoencoders work
  • recognize how principal component analysis works for dimensionality reduction
  • process data to perform principal component analysis
  • implement dimensionality reduction using principal component analysis with scikit-learn
  • apply autoencoders to perform principal component analysis
  • identify how to use the Fashion MNIST dataset for dimensionality reduction
  • apply autoencoders to images to reconstruct them from lower dimensionality representations
  • define how autoencoders work and their use cases


Framework Connections

The materials within this course focus on the NICE Framework Task, Knowledge, and Skill statements identified within the indicated NICE Framework component(s):

Specialty Areas

  • Software Development