Icon

Feed Forward Neural Network Iris Dataset

Classifying the iris dataset with ANN 4-3-1

Exercise of the L4-DL Deep Learning Specialization course.

The goal is to train a multilayer Perceptron with 4-8-3 layers, using BackPropagation, to classify the Iris dataset.

URL: L4-DL course slides https://www.knime.com/form/material-download-registration

Step 2. Design the Keras model (FFNN 4-8-3)
Step 1. Data preparation and partitioning
Step 3. Train the neural network
Step 4. Apply trained network
Step 5. Inverse transform the predictions
Step 6. Evaluate model accuracy

Classification with FFNN

Train, test and validation sets
Preprocessing
input layer Units: 4
Keras Input Layer
Train with Loss function=Categorical Cross EntropyOptimizer=Adam
Keras Network Learner
Expression
Hidden layerUnits: 8Activation: ReLU
Keras Dense Layer
Many to One
Read the iris dataset
Table Reader
Evaluate model
Scorer
output layerUnits: 3Activation: Softmax
Keras Dense Layer
Number to String
Apply trained network
Keras Network Executor

Nodes

Extensions

Links