Inorganic nanoscale device behaves like a single neuron, opening doors for AI and retinal implants

McGill University researchers have developed a light-detecting nanoscale structure that mimics how a neuron processes information. The neuron-like behavior emerges from the materials themselves, ...
Phys.org

Plush neuron makes AI approachable, simplifies neural networks for middle schoolers

A team at Carnegie Mellon University is helping kids understand artificial intelligence with a soft, squishy, LED-lit neural network. "Everyone, even middle schoolers, needs to know a little about ...
Science Daily

Energy and memory: A new neural network paradigm

Listen to the first notes of an old, beloved song. Can you name that tune? If you can, congratulations -- it's a triumph of your associative memory, in which one piece of information (the first few ...
Ars Technica

Researchers get spiking neural behavior out of a pair of transistors

The growing energy use of AI has gotten a lot of people working on ways to make it less power hungry. One option is to develop processors that are a better match to the sort of computational needs of ...
Medical Xpress

Wireless brain neural signal recorder can track neuron signals without the need for batteries

Researchers have successfully developed a fully embedded wireless brain neural signal recorder. This innovative technology enables real-time recording of brain neural signals generated by the ...
Nature

Evaluating single multiplicative neuron models in physics-informed neural networks for differential equations

Artificial Neural Networks (ANNs), the cornerstone of modern machine learning techniques, are designed through mathematical modeling to emulate the functionality of biological neurons. Demonstrating ...
EurekAlert!

Russian scientists reconstruct dynamics of brain neuron model using neural network

Figure 1. Diagram showing an electrically active cell in a neuronal culture and the process of recording its transmembrane potential for further analysis Neurons are cells that enable the brain to ...
Science Daily

Synchronization in neural nets: Mathematical insight into neuron readout drives significant improvements in prediction accuracy

Researchers applied the mathematical theory of synchronization to clarify how recurrent neural networks (RNNs) generate predictions, revealing a certain map, based on the generalized synchronization, ...
American Institute of Physics

Hybrid convolutional neural network yields energy-efficient approach with analog first layer

Oscillatory retinal neuron networks don’t require external voltage sources and show comparable performance to cutting-edge GPU-based convolutional neural networks, for energy costs thousands of times ...
Ars Technica

A neural brain implant provides near instantaneous speech

Stephen Hawking, a British physicist and arguably the most famous man suffering from amyotrophic lateral sclerosis (ALS), communicated with the world using a sensor installed in his glasses. That ...
Nature

Convolutional neural network models describe the encoding subspace of local circuits in auditory cortex

Convolutional neural networks (CNNs) provide powerful models of neural sensory encoding, but their complexity makes it difficult to discern computations that support their performance. Here, to ...