News

Science Daily

Training algorithm breaks barriers to deep physical neural networks

Researchers have developed an algorithm to train an analog neural network just as accurately as a digital one, enabling the development of more efficient alternatives to power-hungry deep learning ...

Breaking Free from GPU Dependency! Nature Publishes Review on 'Physical Neural Networks': Achieving Large-Scale, Efficient AI Training and Inference

A highly regarded research direction is “Physical Neural Networks” (PNNs), which utilize physical systems like light, ...

WiMi Lays Out Scalable Quantum Convolutional Neural Network to Enhance Image Classification Accuracy and Efficiency

WiMi Hologram Cloud Inc. (NASDAQ: WiMi) ("WiMi" or the "Company"), a leading global Hologram Augmented Reality ("AR") Technology provider, today announced that they are actively exploring Scalable ...
Yahoo Finance

MicroAlgo Inc. Adopts Quantum Phase Estimation (QPE) Method to Enhance Quantum Neural Network Training

SHENZHEN, China, June 6, 2025 /PRNewswire/ -- MicroAlgo Inc. (the "Company" or "MicroAlgo") (NASDAQ: MLGO), explored the possibilities of quantum technology in various application scenarios, ...
The Scientist

Artificial Neural Networks: Learning by Doing

Article reviewed by Grace Lindsay, PhD from New York University. Scientists design ANNs to function like neurons. 6 They write lines of code in an algorithm such that there are nodes that each contain ...

Parallel Computing and Acceleration Techniques for Neural Networks

Therefore, parallel computing and acceleration techniques have become crucial in the research and application of neural networks, as they can significantly enhance the performance and efficiency of ...
pv magazine International

PV energy forecasting based on genetic algorithms, dynamic neural network

Scientists in Spain have used genetic algorithms to optimize a feedforward artificial neural network for the prediction of energy generation of PV systems. Genetic algorithms use “parents” and ...