A photograph of a washing line with pegs to symbolize the SageMaker Linear Learner algorithm

Linear Learner Algorithm

Linear Learner Algorithm is a Supervised Learning algorithm that can be used to solve three types of problems: Binary classification; Multi-class classification; and Regression. The algorithm is trained with lists of data comprising a high dimensional vector x and a label y to learn the equation of the line.

The Linear Learner Algorithm uses Stochastic Gradient Descent to fit a line to the data points.

Attributes

Problem attributeDescription
Data types and formatTabular
Learning paradigm or domainSupervised Learning
Problem typeBinary/multi-class classification, Regression
Use case examplesPredict a numeric/continuous value; Predict if an item belongs to a category

Training

Input data

XY
High dimensional vectorNumeric label
Binary classification0 or 1
Multi-class classification0 to num_class – 1
RegressionReal numbers

Format:

  • recordIO-wrapped protobuf
  • CSV

Model artifacts and inference

DescriptionArtifacts
Learning paradigmSupervised Learning
Request formatrecordIO-wrapped protobuf, CSV, JSON
ResultRegression: predicted score
Binary Classification: predicted label 0 or 1 and the strength of the prediction.
Multi-class Classification: predicted label and a list of scores for each class showing the strength of the prediction.

Processing environment

For training the Linear Learner Algorithm single or multi-machine CPU and GPU instances can be used. The same can be used for inferencing with GPU providing little or no improvement over CPU instances.

Video

Amazon SageMaker’s Built-in Algorithm Webinar Series: Linear Learner

This is a 58.54 minutes video from AWS.

Credits

Pegs on clothes line photo by Kyle Arcilla on Unsplash

Similar Posts