The hands-on workshop will provide a gentle but rigorous technical introduction to Deep Learning. The first part of the workshop will emphasize building sound technical intuitions for major concepts such as cost function and gradient descent. Using Python,  we will code neural networks from the “ground up” as a way of deepening mathematical concepts and computational techniques. During the second part of the workshop we will apply libraries such as Keras and Tensorflow to perform deep learning tasks on several data sets. During the third part of the workshop we will deepen our knowledge by considering examples of RNN and CNNs.
This chapter 

End-to-End Machine Learning Project

Building a deep learning model is similar to building any other machine learning model. It involves some high level steps that need to be taken in order to design and redesign the model.  The main steps in building a general machine learning model include:
  1. Splitting the data into train and test data
  2. Train a machine learning model
  3. Evaluate the model on the test data
In addition to the above steps, there are some specific steps that need to be taken to build a machine learning model in Python:
  1. Importing required libraries in Python
  2. Importing the data
  3. Cleaning the data
  4. Splitting the data into train and test data
  5. Create a machine learning model
  6. Train/fit the model
  7. Evaluate the performance of the trained model

Setting up the environment

we use Google colab environment to run our Jupyter notebooks. it also has GPUs, but we start with a simple model, and no need to use GPU. GPUs are blah blah and make running the model much faster. If you are interested, go to this reference to learn about how to use GPUs when running machine learning model. 
the notebook is available on Github, a platform to share code with collaborators privately or publicly. THIS IS THE GITHUB LINK

House Price Prediction Using Keras

We will walk you through a hands-on example to apply deep learning on a real-world data set. For this hands-on exercise, we will be using Jupyter notebooks, Keras and TensorFlow.
Unlike most deep learning tutorials, we won’t be using handwritten digits classification from MNIST. We will be using a real estate data to walk you through an applied example in deep learning.