Baidu Encyclopedia version
The feedforward neural network is one of the simplest neural networks, with each neuron layered. Each neuron is only connected to the neurons of the previous layer. Receive the output of the previous layer and output it to the next layer. There is no feedback between the layers. It is one of the most widely used and fastest-developing artificial neural networks. Research from the 20 century 60 era, the current theoretical research and practical applications have reached a high level.
The feedforward neural network is an artificial neural network in which the connections between the nodes cannot form a loop.  Therefore, it is different from recursive neural networks.
Feedforward neural networks are the first and simplest artificial neural network design. In this network, information moves in only one direction, moving forward from the input node, and moving to the output node through hidden nodes (if any). There are no loops or loops in the network.