The forward-forward algorithm looked interesting to me. This page is going to be a summary of my notes about it if I ever get the chance to play with it.
You can find the paper by Geoffrey Hinton at https://www.cs.toronto.edu/~hinton/FFA13.pdf.
Instead of training a whole deep neural network all at once with backpropagation, the forward-forward algorithm trains each layer of the network one at a time.
@article{yaltirakli, title = "Forward Forward algorithm", author = "Yaltirakli, Gokberk", journal = "gkbrk.com", year = "2025", url = "https://www.gkbrk.com/forward-forward-algorithm" }
Gokberk Yaltirakli, "Forward Forward algorithm", January, 2025. [Online]. Available: https://www.gkbrk.com/forward-forward-algorithm. [Accessed Jan. 01, 2025].
Yaltirakli, G. (2025, January 01). Forward Forward algorithm. https://www.gkbrk.com/forward-forward-algorithm
Gokberk Yaltirakli, Forward Forward algorithm, GKBRK.COM (Jan. 01, 2025), https://www.gkbrk.com/forward-forward-algorithm
© 2024 Gokberk Yaltirakli