Corpus ID: 237491974

Physics-AI Symbiosis

@article{Jalali2021PhysicsAIS,
  title={Physics-AI Symbiosis},
  author={Bahram Jalali and Achuta Kadambi and Vwani P. Roychowdhury},
  journal={ArXiv},
  year={2021},
  volume={abs/2109.05959}
}
The phenomenal success of physics in explaining nature and designing hardware is predicated on efficient computational models. A universal codebook of physical laws defines the computational rules and a physical system is an interacting ensemble governed by these rules. Led by deep neural networks, artificial intelligence (AI) has introduced an alternate end-to-end data-driven computational framework, with astonishing performance gains in image classification and speech recognition and fueling… Expand

Figures from this paper

References

SHOWING 1-10 OF 33 REFERENCES
Discovering physical concepts with neural networks
TLDR
This work models a neural network architecture after the human physical reasoning process, which has similarities to representation learning, and applies this method to toy examples to show that the network finds the physically relevant parameters, exploits conservation laws to make predictions, and can help to gain conceptual insights. Expand
Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations
  • M. Raissi
  • Mathematics, Computer Science
  • J. Mach. Learn. Res.
  • 2018
TLDR
This work puts forth a deep learning approach for discovering nonlinear partial differential equations from scattered and potentially noisy observations in space and time by approximate the unknown solution as well as the nonlinear dynamics by two deep neural networks. Expand
Perceiving Physical Equation by Observing Visual Scenarios
TLDR
This paper introduces a new challenging problem of inferring invariant physical equation from visual scenarios by imitating the actions of an observer and a physicist in the real world and presents a novel pipeline comprised of an Observer Engine and a Physicist Engine. Expand
Distilling Free-Form Natural Laws from Experimental Data
TLDR
This work proposes a principle for the identification of nontriviality, and demonstrated this approach by automatically searching motion-tracking data captured from various physical systems, ranging from simple harmonic oscillators to chaotic double-pendula, and discovered Hamiltonians, Lagrangians, and other laws of geometric and momentum conservation. Expand
Newton vs the machine: solving the chaotic three-body problem using deep neural networks
TLDR
This work shows that an ensemble of solutions obtained using an arbitrarily precise numerical integrator can be used to train a deep artificial neural network (ANN) that, over a bounded time interval, provides accurate solutions at fixed computational cost and up to 100 million times faster than a state-of-the-art solver. Expand
Visual Physics: Discovering Physical Laws from Videos
TLDR
This paper teaches a machine to discover the laws of physics from video streams with no prior knowledge of physics, beyond a temporal stream of bounding boxes, and evaluates its ability to discover physical laws on videos of elementary physical phenomena. Expand
Scaling for edge inference of deep neural networks
TLDR
There are increasing gaps between the computational complexity and energy efficiency required for the continued scaling of deep neural networks and the hardware capacity actually available with current CMOS technology scaling, in situations where edge inference is required. Expand
Inverse-designed metastructures that solve equations
TLDR
A metamaterial platform capable of solving integral equations using monochromatic electromagnetic fields is introduced and is experimentally demonstrated at microwave frequencies through solving a generic integral equation and using a set of waveguides as the input and output to the designed metastructures. Expand
Brain-inspired automated visual object discovery and detection
TLDR
This paper leverages the availability of the Internet to develop a scalable framework for unsupervised learning of object prototypes—brain-inspired flexible, scale, and shift invariant representations of deformable objects comprised of parts, their different configurations and views, and their spatial relationships. Expand
Neuromorphic photonics with electro-absorption modulators.
TLDR
This work develops a model for absorption modulators in an electro-optic fully connected neural network, including noise, and compares the network's performance with the activation functions produced intrinsically by five types of absorption modulator. Expand
...
1
2
3
4
...