Example: Predicting Iris Flower Class

Data

Network

  • Four input features
  • Two hidden layers
  • Three output units: one for each class, encoding the probability for each class
  • network.txt

Training Details

Details

This model predicts the type of iris based on four observed features. The desired output is a single sparse categorical value (translated from a string to a natural number)

Experiment Suggestion

Try changing the hidden layers and numbers of units to see if the accuracy changes

Scikit-Learn Models

Interactive Notebook Tutorial

Tutorial Notebook


This site uses Just the Docs, a documentation theme for Jekyll.