Building Unsupervised Learning Models with TensorFlow
Unsupervised learning techniques work with huge data sets to find patterns within the data. This course teaches you the details of clustering and autoencoding, two versatile unsupervised learning techniques, and how to implement them in TensorFlow.
What you'll learn
Unsupervised learning techniques are powerful, but under utilized and often not well understood. In this course, Building Unsupervised Learning Models with TensorFlow, you'll learn the various characteristics and features of clustering models such as K-means clustering and hierarchical clustering.
First, you'll dive into building a k-means clustering model in TensorFlow.
Next, you'll discover autoencoders in detail, which are a type of artificial neural network used for unsupervised learning.
Finally, you'll explore encodings or representation of data for dimensionality reduction of problems.
By the end of this course, you'll have a better understanding of how you can work with unlabeled data using unsupervised learning techniques.
Table of contents
- Version Check 0m
- Prerequisites and Required Software 4m
- Supervised Learning 6m
- Unsupervised Learning 6m
- Introduction to Clustering 3m
- Minimize Intra-cluster Similarity; Maximize Inter-cluster Similarity 2m
- The Intuition Behind How Autoencoders Work 3m
- Understanding Principal Components Analysis 7m
- Dimensionality Reducing Using Autoencoders 6m
- The Intuition Behind K-means Clustering 5m
- Setting up for K-means Clustering Demos 2m
- Demo: K-means Clustering on 1D Arrays 8m
- K-means Clustering: Algorithm and Design Choices 5m
- Demo: K-means Clustering on 2D Arrays 7m
- Hyperparameter Tuning 6m
- Demo: K-means Clustering on the MNIST Dataset 7m
- Demo: Tweaking the Algorithm on the MNIST Dataset 5m
- Understanding Hierarchical Clustering 5m
- Use Cases of Clustering 2m
- Autoencoders as an Unsupervised Learning Technique 2m
- Autoencoders Learn the Input to Reproduce at the Output 3m
- Principal Components Analysis 4m
- Demo: Implementing PCA Using Matplotlib 7m
- The Undercomplete Autoencoder 6m
- Demo: Implementing an Autoencoder to Perform PCA 8m
- Demo: Implementing the Stacked Autoencoder 11m
- Demo: Implementing a Stacked Autoencoder with Dropout 4m
- Demo: Implementing a Denoising Autoencoder 3m
- Denoising Autoencoders and Unsupervised Pre-training 3m
- Use Cases of Autoencoders 4m