Dimensionality Reduction

Artificial Intelligence (AI) Patterns, Neurons and Neural Networks > Data Wrangling Patterns > Dimensionality Reduction


Dimensionality Reduction

How can the dimensionality of a dataset be reduced so that the reduced feature space does not lose its intrinsic characteristics?


The use of a dataset comprised of a multi-dimensional feature space for neural network training and subsequent prediction not only requires excessive processing and memory resources, but also takes a long time.


The input feature space is converted into a smaller feature space by learning a compressed representation of the input feature space.


The input dataset is compressed into a smaller dataset through the use of an AutoEncoder neural network.












A data scientist prepares a dataset comprised of a large number of features (1). The dataset is then used to train a neural network (2, 3). The resulting network takes longer to train and carry out predictions, and requires increased computing resources and memory (4).

Module 12: Fundamental Service API Design & Management

This pattern is covered in Artificial Intelligence Module 2: Advanced Artificial Intelligence.

For more information regarding the Machine  Learning Specialist curriculum, visit www.arcitura.com/artificialintelligence.