Concept icon
Concept

Domain-Designed Features Can Lower the Amount of Training Data Needed

When labeled data is limited, carefully designed features or structures can make the learning task easier and reduce the sample size needed to get useful performance. In speech tasks, mel-frequency cepstral coefficients can suppress details that are less important, such as speaker-specific pitch or room effects, while phoneme-like categories give the model a more compact way to represent recurring sound units.

0

1

Concept icon
Updated 2026-08-12

Contributors are:

Who are from:

Tags

Machine Learning

Deep Learning

Supervised Learning

Dive into Deep Learning @ D2L

Data Science

Machine Learning Strategy

Machine Learning Yearning @ DeepLearning.AI