How I achieved a bronze medal in Kaggle’s playground competition 4.2 concerning obesity

I really enjoy entering Kaggle’s playground competitions because they help me to stay abreast of current topics in machine learning. In this month’s competition was to predict whether an individual is obese.

I have used Python’s jax and flax’s libraries to code a multilayer perceptron using a softmax activation function and an adam optimizer.

I have written the code in Python and have stored the Jupyter Notebook that the code was written in in my Kaggle account.

The first thing that I did after creating the Jupyter Notebook was to import the libraries that I would need to execute the program, being:-

1. Numpy to create numpy arrays and perform numeric computations,
2. Pandas to create dataframes and process data,
3. Scipy to perform scientific computations,
4. Sklearn to provide machine learning functionality,
5. Jax to provide deep learning functionality and to perform numeric computations,
6. Flax to create the neural network,
7. Optax to provide the optimizer in the neural network,
8. Matplotlib to visualise the data, and