12 Aug Deep Learning programming
Lesson Overview: In this lesson, we are going to have an introduction to Deep Learning programming on Keras. Before to that, we will introduce some of the applications of the Deep Learning in the area of vision and NLP.
Use Case Description: Predicting the diabetes disease
Programming elements: Keras Basics
Source Code: Provided in the assignment and GitHub repo.
Exericise:
1. Use the use case in the class (DL_Lesson_1.ipynb & diabetes.csv):
a. Add more Dense layers to the existing code and check how the accuracy changes.
b. Add the validation_data=(X_test, Y_test) attribute to .fit() method.
c. Plot the accuracy for training and validation (one plot for both: train and test accuracy).
d. Plot the loss for training and validation (one plot for both: train and test loss).
e. Normalize the data before feeding to the model and check how the normalization changes your accuracy sue the StandardScaler() from scikit learn.
