Define shallow neural network architectures and algorithms

`network` | Create custom shallow neural network |

Create and learn the basic components of a neural network object.

**Configure Shallow Neural Network Inputs and Outputs**

Learn how to manually configure the network before
training using the `configure`

function.

**Understanding Shallow Network Data Structures**

Learn how the format of input data structures affects the simulation of networks.

**Edit Shallow Neural Network Properties**

Customize network architecture using its properties and use and train the custom network.

**Adaptive Neural Network Filters**

Design an adaptive linear system that responds to changes in its environment as it is operating.

Learn the architecture, design, and training of perceptron networks for simple classification problems.

**Classification with a Two-Input Perceptron**

A two-input hard limit neuron is trained to classify four input vectors into two categories.

A 2-input hard limit neuron is trained to classify 5 input vectors into two categories.

A 2-input hard limit neuron is trained to classify 5 input vectors into two categories.

**Linearly Non-separable Vectors**

A 2-input hard limit neuron fails to properly classify 5 input vectors because they are linearly non-separable.

Learn to design and use radial basis networks.

This example uses the NEWRB function to create a radial basis network that approximates a function defined by a set of data points.

**Radial Basis Underlapping Neurons**

A radial basis network is trained to respond to specific inputs with target outputs.

**Radial Basis Overlapping Neurons**

A radial basis network is trained to respond to specific inputs with target outputs.

This example uses functions NEWGRNN and SIM.

This example uses functions NEWPNN and SIM.

Use probabilistic neural networks for classification problems.

**Generalized Regression Neural Networks**

Learn to design a generalized regression neural network (GRNN) for function approximation.

**Learning Vector Quantization (LVQ) Neural Networks**

Create and train a Learning Vector Quantization (LVQ) Neural Network.

An LVQ network is trained to classify input vectors according to given targets.

Design a linear network that, when presented with a set of given input vectors, produces outputs of corresponding target vectors.

This example illustrates how to design a linear neuron to predict the next value in a time series given the last five values.

This example shows how an adaptive linear layer can learn to predict the next value in a signal, given the current and last four values.

**Workflow for Neural Network Design**

Learn the primary steps in a neural network design process.

Learn about a single-input neuron, the fundamental building block for neural networks.

Learn architecture of single- and multi-layer networks.

**Custom Neural Network Helper Functions**

Use template functions to create custom functions that control algorithms to initialize, simulate, and train your networks.