image
MNIST Classification
Start course
Difficulty
Beginner
Duration
1h 19m
Students
1070
Ratings
4.8/5
Description

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

Transcript

Hello and welcome to this video on Machine Learning on Pixels. In this video, we will see how to feed images to a fully connected neural network and we will also see how to do that with python. In the last lecture, we learnt how to use pixels as features by simply unrolling an image into a long sequence of numbers. We've also learnt that the pixels are usually stored as unsigned eight bit integers. IE numbers that go from zero to 55.

And that we need to rescale them in order to pass them to a neural network. Rescaling and reshaping the image allows us to feed each image as a single long vector to the neural network. The size of the input layer is therefore equal to the number of pixels in the image, which is 784 and the size of the output is equal to the number of classes we have in our problem. In this case, 10, the number of digits between zero and nine. In this video, we've learnt how to design a fully connected neural network in order to classify a hand-written digit of the MNIST data set. Thank you for watching and see you in the next video.

About the Author
Students
9728
Courses
8
Learning Paths
8

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.