...
Addendum
Forward-Forward Algorithm
https://medium.com/@Mosbeh_Barhoumi/forward-forward-algorithm-ac24d0d9ffd
The forward-forward algorithm uses a custom loss function that compares the mean square value of the activations for positive and negative samples.
The network optimizes this loss function by performing gradient calculations and optimization steps on the trainable weights of the dense layer.
...
Extending the Forward Forward Algorithm
https://arxiv.org/abs/2307.04205
The Forward Forward algorithm (Geoffrey Hinton, 2022-11) is an alternative to backpropagation for training neural networks (NN)
Backpropagation - the most widely successful and used optimization algorithm for training NN - has 3 important limitations ...
Hinton's paper: https://www.cs.toronto.edu/~hinton/FFA13.pdf
Discussion: https://bdtechtalks.com/2022/12/19/forward-forward-algorithm-geoffrey-hinton
...
#GeoffHinton #ForwardPropagation #NeruralNetworks #parametrization #BackproPagation #LossFunction
