Exercise 1
Start course
1h 19m

In this course, discover convolutions and the convolutional neural networks involved in Data and Machine Learning. Introducing the concept of tensor, which is essential for everything that follows.

Learn to apply the right kind of data such as images. Images store their information in pixels, but you will discover that it is not the value of each pixel that matters.

Learning Objectives

  • Understand how convolutional neural networks are essential to the fundamentals of Data and Machine Learning.

Intended Audience


Hey guys, welcome back. In this video, we will review exercise one in section six. Exercise one is another of those exercises where we do a little bit of role-playing, so imagine you're hired by a shipping company that is trying to route their packages, their parcels in an automated way. The simplest way to do that is to read the zipcode which is a series of numbers, printed on the package or on the envelope. So what they'd like to do is build an image recognition system that will read their digit from the zipcode. Luckily, you can rely on the MNIST data set. So what we're going to do is expand on what we've done in class by building a convolutional neural network with at least two convolutional layers and two pooling layers before the fully connected. So in particular, this is the architecture. 

We'll start from what we've have just built. We'll insert an additional Conv2D, convolutional two-dimensional layer after the first MaxPool, then insert the second MaxPool and the activation layer. We'll retrain the model and compare the performances of this model with the previous model. Also, we're asked to compare the number of parameters, whether there are more less and why? And we are asked to compare the training time. Finally, we're asking if it performs better or worse than the previous model. So 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.