neural networks tagged posts

Programmable photonic chip uses light to accelerate AI training and cut energy use

Penn engineers first to train AI at lightspeed
Postdoctoral fellow Tianwei Wu (left) and Professor Liang Feng (right) in the lab, demonstrating some of the apparatus used to develop the new, light-powered chip. Credit: Sylvia Zhang.

Penn Engineers have developed the first programmable chip that can train nonlinear neural networks using light—a breakthrough that could dramatically speed up AI training, reduce energy use and even pave the way for fully light-powered computers.

While today’s AI chips are electronic and rely on electricity to perform calculations, the new chip is photonic, meaning it uses beams of light instead. Described in Nature Photonics, the chip reshapes how light behaves to carry out the nonlinear mathematics at the heart of modern AI.

“Nonlinear functions are critical for training deep neural networks,”...

Read More

AI Shines a New Light on Exoplanets

Comparison of the solution from the scattering PINN with a higher accuracy PINN with fixed parameters. Credit: Monthly Notices of the Royal Astronomical Society (2024). DOI: 10.1093/mnras/stae1872

Researchers from LMU, the ORIGINS Excellence Cluster, the Max Planck Institute for Extraterrestrial Physics (MPE), and the ORIGINS Data Science Lab (ODSL) have made an important breakthrough in the analysis of exoplanet atmospheres.

Using physics-informed neural networks (PINNs), they have managed to model the complex light scattering in the atmospheres of exoplanets with greater precision than has previously been possible.

This method opens up new opportunities for the analysis of exoplanet atmospheres, especially with regard to the influence of clouds, and could significantly improv...

Read More

Neural Networks Made of Light

Artistic illustration of a neuromorphic system of waveguides carrying light.© Clara Wanjura

Scientists propose a new way of implementing a neural network with an optical system which could make machine learning more sustainable in the future. The researchers at the Max Planck Institute for the Science of Light have published their new method in Nature Physics, demonstrating a method much simpler than previous approaches.

Machine learning and artificial intelligence are becoming increasingly widespread with applications ranging from computer vision to text generation, as demonstrated by ChatGPT. However, these complex tasks require increasingly complex neural networks; some with many billion parameters...

Read More

Neural Networks made of Light: Research team develops AI System in Optical Fibers

Neural networks made of light: Research team develops AI system in optical fibers
System training and solving the n-bit parity problem. A) Flowchart of the digital processing layers to interpret the system readout. The training is performed offline using bin selection and linear regression. A simple search algorithm iterates through different frequency bin combinations (see Experimental Section). For each combination, linear regression is used to predict the label (or value) of an inference task. The prediction error was estimated through cross-validation of subsets of the training data. The best-performing combination of bins (i.e., lowest loss) defines an inference-ready system configuration. B) Experimentally measured operation fidelity associated with the n-bit parity problem for increasing bit length and system nonlinearity...
Read More