Fish is drinking coffee and reading about dreams. Fish do not understand the concept of dream, but feels that they understand the concept of overfitting. Sometimes something looks like a worm, moves like a worm, but it is not a worm.
Here we go:
They (humanz) say that people are superstitious because human brain sometimes creates wrong links between events. And probably due to the fact, that it is difficult to re-run part of life with different parameters - not everybody is willing to test if supersition really works or not, for example - in some kind of sports competition.
The question begs - how does the brain deals with such issue and one of the possible answers is - dreaming.
The most common way to tackle overfitting is to add some noise to the learning process, to make it harder for the neural network to focus on irrelevant detail. In practice, researchers add noise to images or feed the computer with corrupted data and even remove random nodes in the neural network, a process known as dropout.
In human terms, this would be equivalent to forcing Michael Jordan to wear different combinations of shorts or making Serena Williams change her socks or Goran Ivanisevic adopting random routines on game days. This would make it much less likely that they would focus on a specific irrelevant detail.
Dreams perform the same function for the brain, says Hoel: “The purpose is to provide 'out-of-distribution' simulations specifically to prevent overfitting and improve generalization.”
How Artificial Neural Networks Paved the Way For A Dramatic New Theory of Dreams
Photo by Megan Thomas on Unsplash