Cellular automata as convolutional neural networks

@article{Gilpin2019CellularAA,
  title={Cellular automata as convolutional neural networks},
  author={William Gilpin},
  journal={Physical review. E},
  year={2019},
  volume={100 3-1},
  pages={
          032402
        }
}
  • William Gilpin
  • Published 2019
  • Physics, Computer Science, Medicine
  • Physical review. E
  • Deep-learning techniques have recently demonstrated broad success in predicting complex dynamical systems ranging from turbulence to human speech, motivating broader questions about how neural networks encode and represent dynamical rules. We explore this problem in the context of cellular automata (CA), simple dynamical systems that are intrinsically discrete and thus difficult to analyze using standard tools from dynamical systems theory. We show that any CA may readily be represented using a… CONTINUE READING
    A Local Approach to Forward Model Learning: Results on the Game of Life Game
    • 10
    • PDF
    Lenia and Expanded Universe
    • 1
    • PDF
    Towards Automated Statistical Physics : Data-driven Modeling of Complex Systems with Deep Learning
    Deep reconstruction of strange attractors from time series.
    Image segmentation via Cellular Automata
    Recent Trends in Modelling and Simulation with Machine Learning
    Message Passing Neural Processes
    CURIE: A Cellular Automaton for Concept Drift Detection
    Deep learning predictions of sand dune migration

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 48 REFERENCES
    Deep Learning
    • 12,587
    • PDF
    Bayesian learning for neural networks
    • 3,145
    • PDF
    Statistical mechanics of cellular automata
    • 2,484
    • PDF
    Approximation by superpositions of a sigmoidal function
    • 5,314
    • PDF
    R
    • 136,232
    • PDF
    Computation at the edge of chaos: phase transitions and emergent computation
    • 1,442
    • PDF
    Deep learning in fluid dynamics
    • 184
    • PDF