170 likes | 187 Views
Explore the use of Recurrent Neural Networks (RNN) for sequence learning, including definitions, features, training processes, limitations, and applications like outlier detection and data inference. Understand RNN's ability to remember past inputs and infer relationships between time series data.
E N D
A critical review of RNN for sequence learningZachary C. Lipton zlipton@cs.ucsd.edu
Timeseries • Definition:A time series is a series of datapoints indexed (or listed or graphed) in time order. It is a sequence of discrete-time data. • Feature: data points space sample from continuous real-word process • Example: stillimagesthatcomprisetheframesofvideos, clinicalmediadata,naturallanguage
Neural Networks • Activationfunction: add the non-linear elements in network
Neural Networks • Activationfunction: add the non-linear elements in network
Neural Networks • Training process: backpropagation algorithm • Gradient decent + Chain rule • Eg: partialderivativeof e=(a+b)*(b+1) respective with respect to a and b
Neural Networks • Training process: backpropagation algorithm
Neural Networks • Training process: backpropagation algorithm
Neural Networks • Training process: backpropagation algorithm
Neural Networks • Training process: backpropagation algorithm
Neural Networks • Training process: backpropagation algorithm
What is RNN? • Feedforward neural network with inclusion of edge that span adjacent step times. • Input for every time step contains the input of temporary time step and the output of last time step.
What is RNN? • Training method: backporpagation , gradient decent. • Limitations: Vanishing gradients.
Vanishing gradient • loss function: • partial derivative of output: • partial derivative of (t-1) layer: • partial derivative of (t-q) layer: • relationship of gradients between (t-q) and t layer:
LSTM (long short-term memory) • To solve the problem of vanishing gradient
RNNs for Outlier Detection • Classification problem • Training RNN weights to minimise the error by normal data. • Since RNN attempts to represent the input patterns in the output, representing outliers are less well produced by the trained RNN have a higher reconstruction error.
Conclusion • RNN can remember previous input. • When the problems involve continuous, prior knowledge related task, it could show advanced capability. • RNN is a data inference method, which can get the probability disribution function from x(t) mapping to y(t).--- finding the relationship between 2 time series.