Beginning Anomaly Detection Using Python-Based Deep Learning by Sridhar Alla & Suman Kalyan Adari

Author:Sridhar Alla & Suman Kalyan Adari
Language: eng
Format: epub
ISBN: 9781484251775
Publisher: Apress

What Is a RNN?

You have seen several types of neural networks throughout the book so you know that the high-level representation of neural networks looks like Figure 6-5.

Figure 6-5A high-level representation of neural networks

Clearly, the neural network processes input and produces output, and this works on many types of input data with varying features. However, a critical piece to notice is that this neural network has no notion of the time of the occurrence of the event (input), only that input has come in.

So what happens with events (input) that come in as a stream over long periods of time? How can the neural network shown above handle trending in events, seasonality in events, etc.? How can it learn from the past and apply it to the present and future?

Recurrent neural networks try to address this by incrementally building neural networks, taking in signals from a previous timestamp into the current network. Figure 6-6 shows a RNN.

Figure 6-6A recurrent neural network

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.