1. Home
  2. Training Library
  3. Big Data
  4. Courses
  5. Getting Started with Deep Learning: Introduction To Machine Learning

Exercise 1

Developed with
Start course
2h 4m

Machine learning is a branch of artificial intelligence that deals with learning patterns and rules from training data. In this course from Cloud Academy, you will learn all about its structure and history. Its origins date back to the middle of the last century, but in the last decade, companies have taken advantage of the resource for their products. This revolution of machine learning has been enabled by three factors.

First, memory storage has become economic and accessible. Second, computing power has also become readily available. Third, sensors, phones, and web application have produced a lot of data which has contributed to training these machine learning models. This course will guide you to the basic principles, foundations, and best practices of machine learning. It is advisable to be able to understand and explain these basics before diving into deep learning and neural nets. This course is made up of 10 lectures and two accompanying exercises with solutions. This Cloud Academy course is part of the wider Data and Machine Learning learning path.

Learning Objectives

  • Learn about the foundations and history of machine learning
  • Learn and understand the principles of memory storage, computing power, and phone/web applications.

Intended Audience

It is recommended to complete the Introduction to Data and Machine Learning course before taking this course.


The datasets and code used throughout this course can be found in the GitHub repo here.



Hey guys, welcome back. In this video, I will present exercise one of section three on machine learning. This exercise is the first of a few ones where we do a little bit of role playing. And we suggest that you've just been hired at a real estate investment firm where they are asking you to build a model to price houses. So we will have to load the data set where there is information about a set of houses, including the number of bedrooms, the size in square feet, the age of the house, and so on. And you have to build a model, so a regression model, that predicts the price. You're guided through nine different steps from loading the data set, plotting the histogram, which by now you should be familiar with. 

Then you have to create two variables called X and Y. X is a matrix with three columns, the square feet, the bedrooms, and the age. And Y is a single column that contains the price. So X is the input, Y is the target. Then create a linear regression model in Keras with the appropriate number of inputs and outputs. Split the data into train and test with a 20% test size. And train the model on the training set checking the accuracy on the test set. Also check the accuracy on the training set so that you can compare the test and the training set accuracy and see if you're doing well or not. Fact, question seven is about how is your model doing and is the loss growing smaller? And then you can try to improve the model with a few experiments, normalizing the features, use a different value for the learning rate, use a different optimizer. 

And we're well aware that at this point in the course, you don't know yet exactly what the learning rate and the optimizer are. We will see them in detail in section five. But you already can experiment and see what happens if you change them. So to form an intuition about their role. Once you're satisfied, check R2score on the test set. So this is exercise one. As usual, try to do it first and then feel free to watch the solution in the next video. Good luck.


About the Author
Learning Paths

I am a Data Science consultant and trainer. With Catalit I help companies acquire skills and knowledge in data science and harness machine learning and deep learning to reach their goals. With Data Weekends I train people in machine learning, deep learning and big data analytics. I served as lead instructor in Data Science at General Assembly and The Data Incubator and I was Chief Data Officer and co-­founder at Spire, a Y-Combinator-­backed startup that invented the first consumer wearable device capable of continuously tracking respiration and activity. I earned a joint PhD in biophysics at University of Padua and Université de Paris VI and graduated from Singularity University summer program of 2011.