Module 2_ICP 1: Basics in Keras - acikgozmehmet/PythonDeepLearning GitHub Wiki
Basics in Keras
Objectives:
The following topics are covered.
- What is Deep learning
- Application of Deep learning
- A brief introduction to how Deep Learning works
- Introduction to Keras library
- Basic operations in Keras
- Use case: diabetes prediction
Overview
What is Deep Learning?
Deep Learning is the "set of algorithms in machine learning that attempt to learn in multiple levels, corresponding to different levels of abstraction" (much-debated definition)
What is the content of this module?
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.
In Class Programming
1. Use the use case in the class:
a. Add more Dense layers to the existing code and check how the accuracy changes.
Click here to get the source code
The accuracy used to be 0.69 with one Dense layer. Now it is increased to 0.73 by adding 2 more Dense layers to the model.
2. Change the data source to Breast Cancer dataset * available in the source folder and make required changes
Click here to get the source code
Model adopted:
Details of the adopted model:
3. Normalize the data before feeding the data to the model and check how the normalization change your accuracy
from sklearn.preprocessing import StandardScaler sc = StandardScaler()
Click here to get the source code
References
-
TensorFlow for Machine Intelligence (TFFMI)
-
Hands-On Machine Learning with Scikit-Learn and TensorFlow. Chapter 9: Up and running with TensorFlow
-
Fundamentals of Deep Learning. Chapter 3: Implementing Neural Networks in TensorFlow (FODL)
-
Deep Learning with Keras: Implementing deep learning models and neural