neural network

Learning and remembering “on the fly” with a new nanowire “brain” network
Electrodes interact with the nanowire neural network at the heart of the chip. Learning and
These flexible fibers, which are embedded with sensors and light sources, can be used to manipulate and monitor the connections between the brain and the digestive tract. Credits:Image: Courtesy of the researchers
New technology that can probe the neural circuits that influence hunger, mood, and a variety of diseases
These flexible fibers, which are embedded with sensors and light sources, can be used to
AI surprise: Higher visual cognitive functions can arise spontaneously in untrained neural networks
via KAIST AI surprise: Higher visual cognitive functions can arise spontaneously in untrained neural networks
Brain-inspired computers get a training algorithm that greatly boosts efficiency and complex problem-solving
Illustration of the on-chip classification process with the Yin-Yang dataset. Each symbol represents the spike
Breakthrough: Clearing a path for quantum AI demonstrates convolutional neural networks can always be trained on quantum computers
A novel proof that certain quantum convolutional networks can be guaranteed to be trained clears
Astrophysics gets a huge simulation boost: 560 hours of work with current methods now can take 36 minutes
Simulations of a region of space 100 million light-years square. The leftmost simulation ran at
Shrinking the energy use and size of neural network hardware
SEM image of the artificial neuron device. Images courtesy of Nature Nanotechnology   Shrinking the
A new “liquid” neural network learns on the job; not just during its training phase
MIT researchers have developed a neural liquid network that varies its equations' parameters, enhancing its
The world’s fastest and most powerful optical neuromorphic processor for artificial intelligence operates faster than 10 trillion operations per second
Dr Xingyuan (Mike) Xu with the integrated optical microcomb chip, which forms the core part
Photonic networks will really speed up pattern recognition and save energy
Schematic representation of a processor for matrix multiplications which runs on light. Together with an
The promise of binarized neural networks for fast, accurate machine learning applications
via PACIFIC NORTHWEST NATIONAL LABORATORY The promise of binarized neural networks for fast, accurate machine
New artificial intelligence software moves robots assisting humans in warehouse environments MUCH closer
UC Berkeley engineers have created new software that combines neural networks with motion planning software
Understanding when not to trust AI-assisted decision-making
via MIT Understanding when not to trust AI-assisted decision-making A neural network learns when it
Enabling artificial intelligence on household appliances while enhancing data security and energy efficiency
MIT researchers have developed a system, called MCUNet, that brings machine learning to microcontrollers. The
Fewer neurons equal more intelligence with new deep learning models
The team tested their new neural network on an important task: keeping self-driving cars in