Researchers at Skoltech have proposed a new approach to training neural networks for wave propagation in absorbing media. The ...

Nvidia researchers have proposed a neural network-based method for compressing material textures that, in results reported in ...

Neural organoids have been heralded as having huge potential for advancing our knowledge of the brain in several fields.

Neural Texture Compression (NTC) could be a game-changer on par with DLSS if it can reduce the VRAM requirement for textures ...

How can AI stabilize the power grid? New research uses biomimetic neural networks to manage the uncertainty of solar and wind energy, reducing hardware costs and preventing blackouts.

A research team at Tohoku University and Future University Hakodate has demonstrated that living biological neurons can be trained to perform a supervised temporal pattern learning task previously ...

Keane, "Amortized Inference for Correlated Discrete Choice Models via Equivariant Neural Networks," NBER Working Paper 35037 (2026), ...

Knowledge distillation is an increasingly influential technique in deep learning that involves transferring the knowledge embedded in a large, complex “teacher” network to a smaller, more efficient ...

When engineers at Sumitomo Riko needed to speed up the design cycle for automotive rubber and polymer components, they turned to AI models trained not just on data but on the fundamental equations of ...

Researchers have developed several data-mechanism hybrid driven methods to improve key variables prediction in process ...

Can living neurons replace AI? A new study shows that biological neural networks (BNNs) can be trained to perform reservoir ...