Computational complexity of neural networks (2022)

Re:Computational complexity of neural networks (2022) by duvenaud on Sunday July 20, 2025 @09:39PM (#44631035)

This is simply wrong. Backprop has the same asymptotic time complexity as forward.

[ Parent | on HN ]

Re:Computational complexity of neural networks (2022) by bobmarleybiceps on Monday July 21, 2025 @12:47AM (#44631884)

I think they're misusing "forward propagation" and "backward propagation" to be basically mean "post training inference" and "training". they seem to be assuming n iterations of the backward pass, which is why it's larger...

[ Parent | on HN ]

Re:Computational complexity of neural networks (2022) by vrighter on Monday July 21, 2025 @03:49AM (#44632721)

n iterations would be a constant factor, which is omitted from asymptotic complexity

[ Parent | on HN ]