# 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…

## References

SHOWING 1-10 OF 33 REFERENCES

Discovering physical concepts with neural networks

- Physics, Computer SciencePhysical review letters
- 2020

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.

Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations

- Mathematics, Computer ScienceJ. Mach. Learn. Res.
- 2018

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.

Perceiving Physical Equation by Observing Visual Scenarios

- Computer ScienceArXiv
- 2018

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.

Distilling Free-Form Natural Laws from Experimental Data

- Physics, MedicineScience
- 2009

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.

Visual Physics: Discovering Physical Laws from Videos

- Computer ScienceArXiv
- 2019

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.

Scaling for edge inference of deep neural networks

- Computer Science
- 2018

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.

Inverse-designed metastructures that solve equations

- MedicineScience
- 2019

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.

Brain-inspired automated visual object discovery and detection

- Computer Science, MedicineProceedings of the National Academy of Sciences
- 2018

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.

Neuromorphic photonics with electro-absorption modulators.

- Medicine, PhysicsOptics express
- 2019

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.

Physics-Based Learned Design: Optimized Coded-Illumination for Quantitative Phase Imaging

- Computer Science, EngineeringIEEE Transactions on Computational Imaging
- 2019

This paper proposes a new data-driven approach for optimizing coded-illumination patterns for an LED array microscope for a given phase reconstruction algorithm that incorporates both the physics of the measurement scheme and the nonlinearity of the reconstruction algorithm into the design problem.