Then, they tried to see if the same neural network could reach optimal settings when trained from scratch. Jacob Springer, computer science student at Swarthmore College This proved that there’s a minimal neural network that can represent the rule of the Game of Life.
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. If the network fails even once, then it is has not correctly learned the rules,” Springer says. It is also very easy to adjust the flexibility of the problem in the Game of Life by modifying the number of timesteps in the future the target deep learning model must predict.Īlso, unlike domains such as computer vision or natural language processing, if a neural network has learned the rules of the Game of Life it will reach 100 percent accuracy. “We can write down by hand a neural network that implements the Game of Life, and therefore we can compare the learned solutions to our hand-crafted one. “We already know a solution,” Jacob Springer, a computer science student at Swarthmore College and co-author of the paper, told TechTalks. There are a few reasons the Game of Life is an interesting experiment for neural networks. With neural networks being very good prediction machines, the researchers wanted to find out whether deep learning models could learn the underlying rules of the Game of Life.Īrtificial neural networks vs the Game of Life Interestingly, no matter how complex a grid becomes, you can predict the state of each cell in the next timestep with the same rules.
You can also use the Game of Life to create very complex pattern, such as this one.
If a dead cell has three live neighbors, it will come to life.īased on these four simple rules, you can adjust the initial state of your grid to create interesting stable, oscillating, and gliding patterns.įor instance, this is what’s called the glider gun.If a live cell has exactly two or three live neighbors, it survives.If a live cell has more than three live neighbors, it dies of overpopulation.If a live cell has less than two live neighbors, it dies of underpopulation.At each timestep, the following simple rules define which cells come to life or stay alive, and which cells die or stay dead:
#Game of life rules 2020 pdf series#
Basically, the Game of Life tracks the on or off state-the life-of a series of cells on a grid across timesteps. What is the Game of Life?īritish mathematician John Conway invented the Game of Life in 1970. Their findings highlight some of the key issues with deep learning models and give some interesting hints at what could be the next direction of research for the AI community. Titled, “ It’s Hard for Neural Networks To Learn the Game of Life,” their research investigates how neural networks explore the Game of Life and why they often miss finding the right solution. It is an interesting idea that shows how very simple rules can yield very complicated results.ĭespite its simplicity, however, the Game of Life remains a challenge to artificial neural networks, AI researchers at Swarthmore College and the Los Alamos National Laboratory have shown in a recent paper. The Game of Life is a grid-based automaton that is very popular in discussions about science, computation, and artificial intelligence. This article is part of our reviews of AI research papers, a series of posts that explore the latest findings in artificial intelligence.
0 kommentar(er)
