Modeling and Prediction with NARX and Time-Delay Networks
|Neural Net Time Series||Solve nonlinear time series problem using dynamic neural networks|
|Time delay neural network|
|Nonlinear autoregressive neural network with external input|
|Nonlinear autoregressive neural network|
|Layer recurrent neural network|
|Distributed delay network|
|Train shallow neural network|
|Generate Simulink block for shallow neural network simulation|
|Add delay to neural network response|
|Remove delay to neural network’s response|
|Convert neural network open-loop feedback to closed loop|
|Convert neural network closed-loop feedback to open loop|
|Plot error histogram|
|Plot input to error time-series cross-correlation|
|Plot linear regression|
|Plot dynamic network time series response|
|Plot autocorrelation of error time series|
|Generate MATLAB function for simulating shallow neural network|
Examples and How To
Make a time series prediction using the Neural Network Time Series App and command-line functions.
Learn to design focused time-delay neural network (FTDNN) for time-series prediction.
Learn multistep neural network prediction.
Create and train a nonlinear autoregressive network with exogenous inputs (NARX).
Create and train a dynamic network that is a Layer-Recurrent Network (LRN).
Simulate and deploy trained shallow neural networks using MATLAB® tools.
Learn how to deploy training of shallow neural networks.
This example illustrates how a NARX (Nonlinear AutoRegressive with eXternal input) neural network can model a magnet levitation dynamical system.
Training Scalability and Efficiency
Use parallel and distributed computing to speed up neural network training and simulation and handle large data.
Save intermediate results to protect the value of long training runs.
Make neural network training more efficient.
Preprocess inputs and targets for more efficient training.
Learn how to manually configure the network before
training using the
Use functions to divide the data into training, validation, and test sets.
Comparison of training algorithms on different problem types.
Learn methods to improve generalization and prevent overfitting.
Learn how to use error weighting when training neural networks.
Learn how to fit output elements with different ranges of values.
Learn how feedforward and recurrent networks work.
Manage time-series data that is available in several short sequences.
Learn how to use utility functions to manipulate neural network data.
List of sample data sets to use when experimenting with shallow neural networks.
Learn properties that define the basic features of a network.
Learn properties that define network details such as inputs, layers, outputs, targets, biases, and weights.