Explore Courses Blog Tutorials Interview Questions
0 votes
in Machine Learning by (19k points)

What is the difference between back-propagation and feed-forward neural networks?

By googling and reading, I found that in feed-forward there is only forward direction, but in back-propagation, once we need to do a forward-propagation and then back-propagation. I referred to this link

  1. Is any other difference other than the direction of flow? What about the weight calculation? The outcome?

  2. Say I am implementing back-propagation, i.e. it contains forward and backward flow. So is back-propagation enough for showing feed-forward?

1 Answer

0 votes
by (33.1k points)

Feed-forward neural networks:

  • The signals in a feedforward network flow in one direction, from input, through successive hidden layers, to the output.

  • The connections between the nodes do not form a cycle as such, it is different from recurrent neural networks. 


Backpropagation is a training algorithm consisting of 2 steps: 

  • Feedforward the values.

  • Calculate the error and propagate it back to the earlier layers. 


Forward-propagation is a part of the backpropagation algorithm but comes before back-propagating the signals from the nodes. The basic type of neural network is a multi-layer perceptron, which is a Feed-forward backpropagation neural network.

Hope this answer helps.

Browse Categories