What is a deep learning model?
The deep in deep learning refers to the successive combination and utilization of various neural network structures to form an architecture that is large and complicated. These large and complicated architectures generally require large amounts of data to train, and the resulting structure is very hard to interpret.
To give an example of the scale and complexity of modern deep learning models, take Google's LeNet (http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Szegedy_Going_Deeper_With_2015_CVPR_paper.pdf) as an example. This model, which can be utilized for object recognition, is depicted here (image courtesy of https://adeshpande3.github.io/adeshpande3.github.io/The-9-Deep-Learning-Papers-You-Need-To-Know-About.html ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access