Deconvolutional Neural Networks (DN)

Deconvolutional networks are convolutional neural networks (CNNs) that work in a reversed process. Even though a DN is similar to a CNN in nature of work, its application in AI is very different. Deconvolutional networks help in finding lost features or signals in networks that deem useful before. A DN may lose a signal due to having been convoluted with other signals. A Deconvolutional network can take a vector and make a picture out of it.