Teaching physics to neural networks removes 'chaos blindness'

Date:
June 19, 2020
Source:
North Carolina State University
Summary:
Teaching physics to neural networks enables those networks to better
adapt to chaos within their environment. The work has implications
for improved artificial intelligence (AI) applications ranging
from medical diagnostics to automated drone piloting.



FULL STORY ========================================================================== Researchers from North Carolina State University have discovered that
teaching physics to neural networks enables those networks to better
adapt to chaos within their environment. The work has implications for
improved artificial intelligence (AI) applications ranging from medical diagnostics to automated drone piloting.


========================================================================== Neural networks are an advanced type of AI loosely based on the way
that our brains work. Our natural neurons exchange electrical impulses according to the strengths of their connections. Artificial neural
networks mimic this behavior by adjusting numerical weights and biases
during training sessions to minimize the difference between their actual
and desired outputs. For example, a neural network can be trained to
identify photos of dogs by sifting through a large number of photos,
making a guess about whether the photo is of a dog, seeing how far off
it is and then adjusting its weights and biases until they are closer
to reality.

The drawback to this neural network training is something called "chaos blindness" -- an inability to predict or respond to chaos in a system.

Conventional AI is chaos blind. But researchers from NC State's Nonlinear Artificial Intelligence Laboratory (NAIL) have found that incorporating
a Hamiltonian function into neural networks better enables them to "see"
chaos within a system and adapt accordingly.

Simply put, the Hamiltonian embodies the complete information about a
dynamic physical system -- the total amount of all the energies present, kinetic and potential. Picture a swinging pendulum, moving back and
forth in space over time. Now look at a snapshot of that pendulum. The
snapshot cannot tell you where that pendulum is in its arc or where it is
going next. Conventional neural networks operate from a snapshot of the pendulum. Neural networks familiar with the Hamiltonian flow understand
the entirety of the pendulum's movement -- where it is, where it will
or could be, and the energies involved in its movement.

In a proof-of-concept project, the NAIL team incorporated Hamiltonian
structure into neural networks, then applied them to a known model of
stellar and molecular dynamics called the He'non-Heiles model. The
Hamiltonian neural network accurately predicted the dynamics of the
system, even as it moved between order and chaos.

"The Hamiltonian is really the 'special sauce' that gives neural
networks the ability to learn order and chaos," says John Lindner,
visiting researcher at NAIL, professor of physics at The College of
Wooster and corresponding author of a paper describing the work. "With
the Hamiltonian, the neural network understands underlying dynamics in
a way that a conventional network cannot.

This is a first step toward physics-savvy neural networks that could
help us solve hard problems." The work appears in Physical Review
Eand is supported in part by the Office of Naval Research (grant N00014-16-1-3066). NC State postdoctoral researcher Anshul Choudhary is
first author. Bill Ditto, professor of physics at NC State, is director
of NAIL. Visiting researcher Scott Miller; Sudeshna Sinha, from the
Indian Institute of Science Education and Research Mohali; and NC State graduate student Elliott Holliday also contributed to the work.


========================================================================== Story Source: Materials provided by North_Carolina_State_University. Note: Content may be edited for style and length.


========================================================================== Journal Reference:
1. Anshul Choudhary, John F. Lindner, Elliott G. Holliday, Scott
T. Miller,
Sudeshna Sinha, William L. Ditto. Physics-enhanced neural networks
learn order and chaos. Physical Review E, 2020; 101 (6) DOI:
10.1103/ PhysRevE.101.062207 ==========================================================================

Link to news story: https://www.sciencedaily.com/releases/2020/06/200619143437.htm

--- up 21 weeks, 3 days, 2 hours, 34 minutes
* Origin: -=> Castle Rock BBS <=- Now Husky HPT Powered! (1337:3/111)