# Data-Centric Approach to Constrained Machine Learning: A Case Study on Conway's Game of Life

arXiv: https://arxiv.org/abs/2408.12778 · HTML: https://mlsanity.com/paper/2408.12778/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 63 references that are in the map.
- First posted on arXiv 23 Aug 2024.

## Builds on (most cited first, 26 of 26)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Adafactor: Adaptive Learning Rates with Sublinear Memory Cost](https://mlsanity.com/paper/1804.04235/) (2018)
- [What is the State of Neural Network Pruning?](https://mlsanity.com/paper/2003.03033/) (2020)
- [Safe Exploration in Continuous Action Spaces](https://mlsanity.com/paper/1801.08757/) (2018)
- [Image to Image Translation for Domain Adaptation](https://mlsanity.com/paper/1712.00479/) (2017)
- [A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models](https://mlsanity.com/paper/2201.05337/) (2022)
- [Lessons from Archives: Strategies for Collecting Sociocultural Data in Machine Learning](https://mlsanity.com/paper/1912.10389/) (2019)
- [Image-to-Image Translation: Methods and Applications](https://mlsanity.com/paper/2101.08629/) (2021)
- [Ethical Machine Learning in Health Care](https://mlsanity.com/paper/2009.10576/) (2020)
- [A Survey on Data Collection for Machine Learning: a Big Data -- AI Integration Perspective](https://mlsanity.com/paper/1811.03402/) (2018)
- [Graph Constrained Reinforcement Learning for Natural Language Action Spaces](https://mlsanity.com/paper/2001.08837/) (2020)
- [Off-Policy Evaluation in Partially Observable Environments](https://mlsanity.com/paper/1909.03739/) (2019)
- [Power Constrained Bandits](https://mlsanity.com/paper/2004.06230/) (2020)
- [A Data-Centric Approach for Training Deep Neural Networks with Less Data](https://mlsanity.com/paper/2110.03613/) (2021)
- [Steady State Analysis of Episodic Reinforcement Learning](https://mlsanity.com/paper/2011.06631/) (2020)
- [It's Hard for Neural Networks To Learn the Game of Life](https://mlsanity.com/paper/2009.01398/) (2020)
- [Expert-Augmented Machine Learning](https://mlsanity.com/paper/1903.09731/) (2019)
- [Are Efficient Deep Representations Learnable?](https://mlsanity.com/paper/1807.06399/) (2018)
- [A Novel Evolution Strategy with Directional Gaussian Smoothing for Blackbox Optimization](https://mlsanity.com/paper/2002.03001/) (2020)
- [Generalization over different cellular automata rules learned by a deep feed-forward neural network](https://mlsanity.com/paper/2103.14886/) (2021)
- [Universal Reinforcement Learning Algorithms: Survey and Experiments](https://mlsanity.com/paper/1705.10557/) (2017)
- [Offline Policy Comparison under Limited Historical Agent-Environment Interactions](https://mlsanity.com/paper/2106.03934/) (2021)
- [A Constrained Consensus Based Optimization algorithm and its Application to Finance](https://mlsanity.com/paper/2110.04499/) (2021)
- [Game of Life on Graphs](https://mlsanity.com/paper/2111.01780/) (2021)
- [Constrained Machine Learning: The Bagel Framework](https://mlsanity.com/paper/2112.01088/) (2021)

## Built on by (most cited first, 2 of 2)

- [Learning Elementary Cellular Automata with Transformers](https://mlsanity.com/paper/2412.01417/) (2024)
- [Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling](https://mlsanity.com/paper/2508.16745/) (2025)

## Abstract (arXiv)

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.