Neural Network: Multi-layer Perceptron (MLP)

[sophryu99]

Multi-layer Perceptron (MLP)

MLP is Class of feedforward artificial neural network (ANN).

• Composed of multiple layers of perceptrons.
• MLP consists of at least three layers of nodes: an input layer, a hidden layer, and an output layer
• Except for the input nodes, each node is a neuron that uses a nonlinear activation function.
• Without the activation function, the model can be classified as a logistic regression
• Utilizes a supervised learning called back-propagation Neural Networks: Back Propagation #29

Types of Layers in MLP

• Input Layer: Input variables, sometimes called the visible layer.
• Hidden Layers: Layers of nodes between the input and output layers. There may be one or more of these layers.
• Output Layer: A layer of nodes that produce the output variables.

[sophryu99]

Terminologies to describe the shape and capability of a neural network

• Size: The number of nodes in the model.
• Width: The number of nodes in a specific layer.
• Depth: The number of layers in a neural network.
• Capacity: The type or structure of functions that can be learned by a network configuration. Sometimes called “representational capacity“.
• Architecture: The specific arrangement of the layers and nodes in the network.
• Batch Size: Number of instances that will be processed for each back propagation run
• Epoch: One run through the whole dataset
• Stopping criteria: The error changes less than epsilon
• Rules of thumb in network design: