Session Ready
Exercise

Create an input layer with multiple columns

In this exercise, you will look at a different way to create models with multiple inputs. This method only works for purely numeric data, but its a much simpler approach to making multi-variate neural networks.

Now you have three numeric columns in the tournament dataset: 'seed_diff', 'home', and 'pred'. In this exercise, you will create a neural network that uses a single input layer to process all three of these numeric inputs.

This model should have a single output to predict the tournament game score difference.

Instructions
100 XP
  • Create a single input layer with 3 columns.
  • Connect this input to a Dense layer with 1 unit.
  • Create a model with input_tensor as the input and output_tensor as the output.
  • Compile the model with 'adam' as the optimizer and 'mean_absolute_error' as the loss function.