• Corpus ID: 245005934

Building Quantum Field Theories Out of Neurons

@article{Halverson2021BuildingQF,
  title={Building Quantum Field Theories Out of Neurons},
  author={James Halverson},
  journal={ArXiv},
  year={2021},
  volume={abs/2112.04527}
}
An approach to field theory is studied in which fields are comprised of N constituent random neurons. Gaussian theories arise in the infinite-N limit when neurons are independently distributed, via the Central Limit Theorem, while interactions arise due to finite-N effects or non-independently distributed neurons. Euclidean-invariant ensembles of neurons are engineered, with tunable twopoint function, yielding families of Euclidean-invariant field theories. Some Gaussian, Euclidean invariant… 

Renormalization in the neural network-quantum field theory correspondence

This work states that changing the standard deviation of the neural network weight distribution corresponds to a renormalization in the space of networks and discusses preliminary numerical results for translation-invariant kernels.

A duality connecting neural network and cosmological dynamics

We demonstrate that the dynamics of neural networks (NNs) trained with gradient descent and the dynamics of scalar fields in a flat, vacuum energy dominated Universe are structurally profoundly

Snowmass White Paper: Cosmology at the Theory Frontier

The precision cosmological model describing the origin and expansion history of the universe, with observed structure seeded at the inflationary cosmic horizon, demands completion in the ultraviolet

On the Dynamics of Inference and Learning

A treatment of this Bayesian updating process as a continuous dynamical system based on examples based on Gaussians and Gaussian Random Processes and inference of the coupling constant in the 1D Ising model.

Characterizing 4-string contact interaction using machine learning

It is argued that the algorithm is manifestly independent of number of punctures and scaling it to characterize the geometry of n -string contact interaction is feasible.

Cluster Algebras: Network Science and Machine Learning

Network analysis methods are applied to the exchange graphs for cluster algebras of varying mutation types and indicates that when the graphs are represented without identifying by permutation equivalence between clusters an elegant symmetry emerges in the quiver exchange graph embedding.

Machine learning Calabi-Yau hypersurfaces

This work revisits the classic database of weighted-Ps which admit Calabi-Yau 3-fold hypersurfaces equipped with a diverse set of tools from the machine-learning toolbox and identifies a previously unnoticed clustering in the Calabi/Yau data.

References

SHOWING 1-10 OF 21 REFERENCES

Quantum Physics: A Functional Integral Point of View

This book is addressed to one problem and to three audiences. The problem is the mathematical structure of modem physics: statistical physics, quantum mechanics, and quantum fields. The unity of

Gaussian Processes for Machine Learning

The treatment is comprehensive and self-contained, targeted at researchers and students in machine learning and applied statistics, and deals with the supervised learning problem for both regression and classification.

“A and B”:

Direct fabrication of large micropatterned single crystals. p1205 21 Feb 2003. (news): Academy plucks best biophysicists from a sea of mediocrity. p994 14 Feb 2003.

Mach

  • Learn. Sci. Tech. 2, 035002
  • 2021

and D

  • O. Samary,
  • 2021

Advances in Neural Information Processing Systems 31

In Advances in Neural Information Processing Systems

Bill Baird { Publications References 1] B. Baird. Bifurcation analysis of oscillating neural network model of pattern recognition in the rabbit olfactory bulb. In D. 3] B. Baird. Bifurcation analysis

JHEP 09

  • 157 (2017), arXiv:1707.00655 [hep-th]; C. R. Brodie, A. Constantin, R. Deen, and A. Lukas, Fortsch. Phys. 68, 1900087 (2020), arXiv:1906.08730 [hep-th]; A. Davies, P. Veličković, L. Buesing, S. Blackwell, D. Zheng, N. Tomašev, R. Tanburn, P. Battaglia, C. Blundell, A. Juhász, M. Lackenby, G. William
  • 2021

arXiv e-prints

  • arXiv:1910.12478
  • 2019