In 1986, three scientists improved backpropagation, making neural networks learn effectively from data

A groundbreaking 1986 technique called backpropagation revolutionized artificial intelligence, enabling computers to learn ...
Nature

Training all-mechanical neural networks for task learning through in situ backpropagation

Recent advances unveiled physical neural networks as promising machine learning platforms, offering faster and more energy-efficient information processing. Compared with extensively-studied optical ...
Nature

Transfer learning with graph neural networks for improved molecular property prediction in the multi-fidelity setting

We investigate the potential of graph neural networks (GNNs) for transfer learning and improved molecular property prediction in the context of funnels or screening cascades characteristic of drug ...
Tech Xplore

Brain-inspired AI architecture could compute faster while using far less power

Spiking neural networks (SNNs) are artificial intelligence (AI) models inspired by how biological neurons communicate with ...
Neuroscience News

Human Memory Limits Make AI Better at Grammar

Researchers build fleeting memory transformers with human-like memory decay, proving memory limits help AI learn grammar ...
Science Daily

Hidden geometry of learning: Neural networks think alike

Engineers have uncovered an unexpected pattern in how neural networks -- the systems leading today's AI revolution -- learn, suggesting an answer to one of the most important unanswered questions in ...
Tech Xplore on MSN

Forgetting may be the secret to better AI language learning

Giving AI a human-like memory limitation may actually help it learn language better. In their new proof-of-principle study, ...
InfoWorld

The most popular neural network styles and how they work

Learn about the most prominent types of modern neural networks such as feedforward, recurrent, convolutional, and transformer networks, and their use cases in modern AI. Neural networks are the ...

Mirendil raises $200M to speed up scientific research with AI

Mirendil Inc., a startup developing artificial intelligence models for scientists, has raised $200 million in funding at a $1 ...
Aerospace and Mechanical Insider on MSN

AI and machine learning transform materials testing

Materials testing remains a cornerstone of engineering and manufacturing, ensuring that components and structures—from ...
The Manila Times

WiMi Develops Quantum Convolutional Neural Network Model for Classical Data Classification

WiMi Hologram Cloud Inc. (NASDAQ: WIMI) ('WIMI' or the 'Company'), a leading global Hologram Augmented Reality ('AR') Technology provider, has completed systematic benchmark testing on fully ...
EurekAlert!

The hidden geometry of learning: neural networks think alike

Penn Engineers have uncovered an unexpected pattern in how neural networks — the systems leading today’s AI revolution — learn, suggesting an answer to one of the most important unanswered questions ...