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.
Citation
If you find this work useful, please cite it as:
@article{yaltirakliwikiforwardforwardalgorithm,
title = "Forward-Forward Algorithm",
author = "Yaltirakli, Gokberk",
journal = "gkbrk.com",
year = "2023",
url = "https://www.gkbrk.com/wiki/forward-forward-algorithm/"
}
Not using BibTeX? Click here for more citation styles.
IEEE Citation Gokberk Yaltirakli, "Forward-Forward Algorithm", December, 2023. [Online]. Available: https://www.gkbrk.com/wiki/forward-forward-algorithm/. [Accessed Dec. 04, 2023].
APA Style Yaltirakli, G. (2023, December 04). Forward-Forward Algorithm. https://www.gkbrk.com/wiki/forward-forward-algorithm/
Bluebook Style Gokberk Yaltirakli, Forward-Forward Algorithm, GKBRK.COM (Dec. 04, 2023), https://www.gkbrk.com/wiki/forward-forward-algorithm/