Input and Output Sequences An RNN can simultaneously take a sequence of inputs and produce a sequence of outputs (see Figure 14-4, top-left network). For example, this type of network is useful for predicting time series such as stock prices: you feed it the prices over the last N days, and it must output the prices shifted by one day into the future (i.e., from N – 1 days ago to tomorrow). Alternatively, you could feed the network a sequence of inputs, and ignore all outputs except for the last one (see the top-right network). In other words, this is a sequence-to-vector network. For example, you could feed the network a sequence of words corresponding to a movie review, and the network would output a sentiment score (e.g., from –1 [h...
- 14. Recurrent Neural Networks
- from Hands-On Machine Learning with Scikit-Learn and TensorFlow
- Publisher: O'Reilly Media, Inc.
- Released: March 2017
Share this highlighthttp://www.safaribooksonline.com/a/hands-on-machine-learning/10960874/