# what is difference between multilayer perceptron and multilayer neural network?

When do we say that a artificial neural network is a multilayer Perceptron?

And when do we say that a artificial neural network is a multilayer?

Is the term perceptron related to learning rule to update the weights?

Or It is related to neuron units?

A perceptron is always feedforward, that is, all the arrows are going in the direction of the output. Neural networks in general might have loops, and if so, are often called recurrent networks. A recurrent network is much harder to train than a feedforward network.

In addition, it is assumed that in a perceptron, all the arrows are going from layer $i$ to layer $i+1$, and it is also usual (to start with having) that all the arcs from layer $i$ to $i+1$ are present.

Finally, having multiple layers means more than two layers, that is, you have hidden layers. A perceptron is a network with two layers, one input and one output. A multilayered network means that you have at least one hidden layer (we call all the layers between the input and output layers hidden).

When do we say that a artificial neural network is a multilayer Perceptron?

Artificial neural network, which has input layer, output layer, and two or more trainable weight layers (constisting of Perceptrons) is called multilayer perceptron or MLP.

And when do we say that a artificial neural network is a multilayer?

You can say it is a multilayer network, if it has two or more trainable layers.

Is the term perceptron related to learning rule to update the weights?

No. There are many different learning rules, that can be applied to change weights in order to teach perceptron. Term perceptron does not entail any specific learning rule by itself.

Or It is related to neuron units?

Not sure what you mean by this.

You can read more in this free book http://www.dkriesel.com/_media/science/neuronalenetze-en-zeta2-2col-dkrieselcom.pdf

• I think your count of layers is off: your definition would require a min of four layers whereas AFAIK an MLP actually only requires a min of three layers: an input, a single hidden and an output. – javadba Jun 13 '19 at 22:38

From Wikipedia:

In the context of neural networks, a perceptron is an artificial neuron using the Heaviside step function as the activation function.

So the perceptron is a special type of a unit or a neuron. Hence multilayer perceptron is a subset of multilayer neural networks.

• please say some reference for basic concept of neural network. (PDF Book) – Mohammad Feb 23 '16 at 16:46