Harvard University physicists have developed a simplified, physics-based mathematical model to better understand how neural networks learn. The approach mirrors historical scientific breakthroughs, ...

Artificial intelligence systems based on neural networks—such as ChatGPT, Claude, DeepSeek or Gemini—are extraordinarily ...

Researchers use statistical physics and "toy models" to explain how neural networks avoid overfitting and stabilize learning in high-dimensional spaces.

The demand for immersive, realistic graphics in mobile gaming and AR or VR is pushing the limits of mobile hardware. Achieving lifelike simulations of fluids, cloth, and other materials historically ...

The 2024 Nobel Prize in Physics has been awarded to scientists John Hopfield and Geoffrey Hinton “for foundational discoveries and inventions that enable machine learning with artificial neural ...

Now, artificial intelligence (AI) tools are providing powerful new ways to address long-standing problems in physics. “The ...

The neural networks infer two basic types of local interaction rules: distance-based rules that set spacing, velocity-based rules that align headings, as well as their combination. The team also ...

A neural network is a machine learning model originally inspired by how the human brain works (Courtesy: Shutterstock/Jackie Niam) Precision measurements of theoretical parameters are a core element ...

Georgia Tech researchers demonstrated the mechanics behind neural tube closure, which can lead to severe or fatal birth ...

In about one out of every 1,000 pregnancies, the neural tube, a key nervous system structure, fails to close properly. Georgia Tech physicists are now helping explain why this happens, having ...