Re:What We Know About LLMs (A Primer)
by moffkalast on Tuesday July 25, 2023 @07:08PM
(#36870983)
Isn't dropout just there to avoid overfitting? This is more like a mixture of experts type architecture.
That is one lens to view it through. Co-adaptation reduction is another, and it is an intuitive one: generalization ability is improved if a neuron has to be predictive in multiple contexts, and can't rely on other neurons to lift all the weight, if you pardon the pun.
Improving neural networks by preventing co-adaptation of feature detectors https://arxiv.org/abs/1207.0580
That became popular in neural networks after the introduction of dropout regularization, which forced neurons to "co-adapt" and learn to do each others' jobs. Large, over-specified models also provide a natural setting for co-adaptation.