Get the latest tech news
Why neural networks struggle with the Game of Life (2020)
The Game of Life is based on very simple rules, but artificial neural networks struggle to learn its rules through the classic deep learning training process.
In their work, the researchers first created a small convolutional neural network and manually tuned its parameters to be able to predict the sequence of changes in the Game of Life’s grid cells. The hypothesis suggested that for each large neural network, there are smaller sub-networks that can converge on a solution if their parameters have been initialized on lucky, winning values, thus the “lottery ticket” nomenclature. “The lottery ticket hypothesis proposes that when training a convolutional neural network, small lucky subnetworks quickly converge on a solution,” the authors of the Game of Life paper write.
Or read this on Hacker News
