Recurrent Neural Networks

18. Recurrent Neural Networks#

Often data arise as sequences:

  • Documents are sequence of words, and their relative positions have meaning

  • Time-series such as weather data or financial indices.

  • Recorded speech or music.

  • Handwriting, such as doctor’s notes.

The feature for each observation is a sequence of vectors \(X={X_1,X_2,...,X_L}\)

  • The target Y is often a single variable such as Sentiment, or a one-hot vector for multiclass.

  • Y can also be a sequence, such as the same document in a different language.

image.png

  • The same wights \(W\), \(U\) and \(B\) are used at each step in the sequence - hence the term recurrent.

19. Example (IMDB Reviews)#

image.png image-2.png image-3.png

20. Time Series Forecasting#

image.png image-2.png

21. Traditional autoregression forecaster#

image.png

22. When to use Deep Learning#

image.png

Contents