# Function Approximation Using Multilayer Perceptron — Data

来源：https://www.kaggle.com/competitions/function-approximation-using-multilayer-perceptron/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

Two datasets are given:
* **train.csv**: the training dataset which contains three columns of data. Column 1 and Column 2 are inputs x1 and x2, while Column 3 is the target value y.
* **test.csv**: the testing dataset for evaluating your model. Only two columns of data, i.e., x1 and x2, are given.

You need to produce the estimated value for every sample in the testing dataset using your network and save all estimated values into a file (**submission.csv**). Do not change the order of samples in the testing dataset; otherwise, your submission may get a low score due to the mismatch between your answers and the true answers.