Finding Emergence in Data Using Machine Learning
Author Information
Author(s): Yang Mingzhe, Wang Zhipeng, Liu Kaiwei, Rong Yingqi, Yuan Bing, Zhang Jiang
Primary Institution: Beijing Normal University
Hypothesis
Can a machine learning framework effectively quantify causal emergence and model macro-dynamics in complex systems?
Conclusion
The proposed machine learning framework successfully quantifies causal emergence and models macro-dynamics, demonstrating improved generalization across diverse conditions.
Supporting Evidence
- The framework effectively captures emergent dynamics from both simulated and real data.
- NIS+ shows superior generalization capabilities compared to alternative approaches.
- Experiments demonstrate that maximizing effective information leads to better identification of causal emergence.
- NIS+ can learn from noisy data and still identify the underlying dynamics.
- The framework has been validated on real fMRI data from 830 individuals.
Takeaway
This study created a smart computer program that helps us understand how complex systems behave by looking at patterns in data, like how a flock of birds moves together.
Methodology
The study developed a machine learning framework called NIS+ that learns macro-dynamics and quantifies causal emergence from time series data.
Potential Biases
Potential overfitting due to the complexity of the model and the amount of training data required.
Limitations
The framework requires a large amount of training data, which may not be feasible in many real-world cases, and the interpretability of the models remains a challenge.
Participant Demographics
830 subjects from fMRI studies, watching the same movie clip.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website