Feedforward Neural NetworkIt is a relatively simple artificial neural network, whose internal parameters propagate unidirectionally from the input layer to the output layer. Unlike recursive neural networks, it does not form a directed loop internally.

Feedforward is also called forward. From the perspective of signal flow, after the input signal enters the network, the signal flow is unidirectional, that is, the signal flows from the previous layer to the next layer until the output layer, and there is no feedback in the connection between any two layers, that is, the signal does not return from the next layer to the previous layer; if viewed from the perspective of input-output relationship, when the input signal enters, the next layer will use the output of the previous layer as input.

In a feedforward neural network, when there is a reverse flow or self-input between layers, the network is called a recurrent neural network. In a deep feedforward network, the chain structure is the connection between layers, where the number of layers indicates the depth of the network.

References

【1】Neural Networks and Deep Learning - Feedforward Neural Networks (Personal Blog)