Convolutional Neural Network
The course is part of this learning path
Convolutional Neural Networks
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.
- Understand how convolutional neural networks are essential to the fundamentals of Data and Machine Learning.
- It is recommended to complete the Introduction to Data and Machine Learning course before starting.
Hello and welcome to this video on convolutional neural networks. In this video we finally bring together all the things we've learned in the past lectures. Tensors, convolutional layers, pooling layers, and recombine them with other ingredients in order to build our first convolutional neural network. Let's start by stacking convolutional and pooling layers together, going from a shallow image to a tensor of smaller size and many more channels. After we do that we can use the pixels in the last pooling layer as the features for a fully connected final stack of layers. The feature extraction part involves convolutional, pooling, and long linear activation functions.
And it transforms an input image in a tensor with many channels that encapsulate pattern matching in their pixels. We can enroll these features onto a long vector like we did initially and connect this vector to the labels using a fully connected layer. We can also stack multiple fully connected layers if you want. Our final network is like a pancake of many layers. The convolutional part dealing with feature extraction and the fully connected part handling the classification. The deeper we go in the network, the richer and more unique are the patterns match. And so more robust the classification will be. In conclusion, in this video we've learned how to stack layers in order to produce a convolutional neural network also using a flattening and a fully connected layer at the end. So thank you for watching and see you in the next video.
About the Author
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.