In this activity, you are going to build and train your first neural network to address a classification problem in order to predict diabetes disease.
This model is quite simple and no heavy computation is needed, so you might be able to run it in your own laptop.
- Dataset: Pima Indian Diabetes from Kaggle (already provided).
- Frameworks: Keras and TensorFlow
- Environment: Conda + Jupyter Notebook (already provided)
- You will need Conda installed
- Check if conda is running:
conda info - Import the environment file:
conda env create -f environment.yaml - Activate your environment:
source activate deep-learning-keras - To deactivate your environment:
source deactivate deep-learning-keras