Data-Centric Approach to Constrained Machine Learning: A Case Study on Conway's Game of Life
This work addresses constrained machine learning problems where limited trainable parameters make rule learning difficult, though it appears incremental as it applies existing data-centric ideas to a specific domain.
This paper tackles the challenge of training minimal neural networks to learn Conway's Game of Life transition rules by proposing a data-centric approach that strategically designs training datasets, showing that this method improves performance regardless of other learning parameters like initialization or optimization algorithms.
This paper focuses on a data-centric approach to machine learning applications in the context of Conway's Game of Life. Specifically, we consider the task of training a minimal architecture network to learn the transition rules of Game of Life for a given number of steps ahead, which is known to be challenging due to restrictions on the allowed number of trainable parameters. An extensive quantitative analysis showcases the benefits of utilizing a strategically designed training dataset, with its advantages persisting regardless of other parameters of the learning configuration, such as network initialization weights or optimization algorithm. Importantly, our findings highlight the integral role of domain expert insights in creating effective machine learning applications for constrained real-world scenarios.