Artificial Intelligence for Big Data
by Anand Deshpande, Manish Kumar, Albenzo Coletta, Giancarlo Zaccone
The need for RNNs
In the case of the feed-forward networks, we consider independent sets of inputs. In the case of image recognition problems, we have input images that are independent of each other in terms of the input dataset. In this case, we consider the pixel matrix for the input image. The input data for one image does not influence the input for the next image that the ANN is trying to recognize. However, if the image is part of a sequence or a frame within a video input, there is a correlation or dependence between one frame to the next frame.
This is also the case in audio or speech input to the ANN. Another limitation of the ANNs we have seen so far is that the length of the input layer needs to be constant. For example, a network ...
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