A trained convolutional layer is made up of many feature detectors, called filters, that slide over an input image as a moving window. We will talk about what's inside a filter in a moment, but for now it can be a black box. Imagine a single filter that has already been trained. Maybe that filter has been trained to detect edges in images, which you might think of as transitions between dark and light. As it passes over the image, its output represents the presence and location of the feature it detects, which can be useful for a second layer of filters. Extending our thought experiment slightly further, now imagine a single filter, in a second convolutional layer, that has also already been trained. Perhaps this new layer has learned to detect right angles, where two edges that have been found by the previous layer are present. On and on we go; as...
- Tech Categories
- Best Sellers
- New Releases
- Books
- Videos
- Audiobooks
Tech Categories Popular Audiobooks
- Articles
- Newsletters
- Free Learning
You're reading from Deep Learning Quick Reference
Mike Bernico is a Lead Data Scientist at State Farm Mutual Insurance Companies. He also works as an adjunct for the University of Illinois at Springfield, where he teaches Essentials of Data Science, and Advanced Neural Networks and Deep Learning. Mike earned his MSCS from the University of Illinois at Springfield. He's an advocate for open source software and the good it can bring to the world. As a lifelong learner with umpteen hobbies, Mike also enjoys cycling, travel photography, and wine making.
Read more about Mike Bernico
Unlock this book and the full library FREE for 7 days
Author (1)
Mike Bernico is a Lead Data Scientist at State Farm Mutual Insurance Companies. He also works as an adjunct for the University of Illinois at Springfield, where he teaches Essentials of Data Science, and Advanced Neural Networks and Deep Learning. Mike earned his MSCS from the University of Illinois at Springfield. He's an advocate for open source software and the good it can bring to the world. As a lifelong learner with umpteen hobbies, Mike also enjoys cycling, travel photography, and wine making.
Read more about Mike Bernico