With the core concepts of autoencoders covered, this chapter focuses on the practical steps involved in constructing your first model designed for feature extraction. We will proceed through the entire workflow, from initial data preparation to extracting and understanding the learned features.
This chapter will guide you through:
3.1 Data Preparation for Autoencoder Training
3.2 Encoder Network Design Choices
3.3 Determining Latent Space Dimensionality
3.4 Decoder Network Design Strategies
3.5 Selecting Appropriate Loss Functions for Autoencoders
3.6 Optimizer Selection and Learning Rate Configuration
3.7 Monitoring Autoencoder Training Progress
3.8 Techniques for Extracting Features from the Bottleneck
3.9 Visualizing Latent Space (When Applicable)
3.10 Hands-on: Feature Extraction from Tabular Data
© 2025 ApX Machine Learning