04 - Neural Network Models

04.01 Simple Neural Network

Learning objective: In this exercise you'll learn how predict the price of a house in Ames (Iowa, USA) given a number of features: size, neighborhood, heating...

Workflow description: This workflow uses a dataset that describes the sale of individual residential properties in Ames, Iowa from 2006 to 2010. One of the columns is the overall condition ranking, with values between 1 and 10.

You'll find the instructions to the exercises in the yellow annotations.

Step 1. RProp MLP Learner

Train a fully connected neural network to predict the overall condition of a house (high/low) (RProp MLP Learner node)

Step 2. MultiLayerPerceptron Predictor

Use the trained model to predict the rank of the houses in the test set (MultiLayerPerceptron Predictor node)

Data Preparation

Step 3. Model evaluation

Evaluate the accuracy of the random forest model (Scorer node)

Step 4. Parameter Optimization Loop Start (Optional)

Build a paramter optimization loop to optimize the number of layers and the number of neurons per layer.

Step 5. Parameter Optimization Loop End (Optional)