Deep Residual Network

What Does Deep Residual Network Mean?

A deep residual network (deep ResNet) is a type of specialized neural network that helps to handle more sophisticated deep learning tasks and models. It has received quite a bit of attention at recent IT conventions, and is being considered for helping with the training of deep networks.


Techopedia Explains Deep Residual Network

In deep learning networks, a residual learning framework helps to preserve good results through a network with many layers. One problem commonly cited by professionals is that with deep networks composed of many dozens of layers, accuracy can become saturated, and some degradation can occur. Some talk about a different problem called "vanishing gradient" in which the gradient fluctuations become too small to be immediately useful.

The deep residual network deals with some of these problems by using residual blocks, which take advantage of residual mapping to preserve inputs. By utilizing deep residual learning frameworks, engineers can experiment with deeper networks that have specific training challenges.


Related Terms

Latest Artificial Intelligence Terms

Related Reading

Margaret Rouse

Margaret Rouse is an award-winning technical writer and teacher known for her ability to explain complex technical subjects to a non-technical, business audience. Over the past twenty years her explanations have appeared on TechTarget websites and she's been cited as an authority in articles by the New York Times, Time Magazine, USA Today, ZDNet, PC Magazine and Discovery Magazine.Margaret's idea of a fun day is helping IT and business professionals learn to speak each other’s highly specialized languages. If you have a suggestion for a new definition or how to improve a technical explanation, please email Margaret or contact her…