Neural Network

Computers destroy humans at chess, but there's not a single one that could go into a house and feed the dog. Intel's research-grade Loihi 2 neuromorphic chips are working on it though, drawing inspiration from nature's greatest necktop supercomputer.

A compelling study indicates Parkinson’s disease could be diagnosed by remotely tracking a person’s breathing patterns. Led by researchers from MIT, the study presents an AI system that uses radio waves to monitor breathing while a person sleeps.

MIT engineers have developed a new type of artificial synapse that’s extremely energy efficient and ultra-fast, processing data a million times faster than synapses in the human brain. The analog device shuttles protons around instead of electrons.

Engineers at MIT have developed a modular computer chip with components that can communicate using flashes of light. This could allow for electronics that can easily be upgraded with new sensors or processors, rather than replacing the whole chip.

A powerful new optical chip can process almost two billion images per second. The device is made up of a neural network that processes information as light without needing components that slow down traditional computer chips, like memory.

At last week's GTC developer conference, Nvidia revealed a nifty AI tool that takes a bunch of 2D photos of the same scene from different angles and almost instantly transforms them into a three-dimensional digital rendering.

Researchers have demonstrated, for the first time, a brain implant turning neural activity into full words. The first participant in the trial, a paralyzed man, can now speak with a vocabulary of 50 words by simply thinking about vocalizing words.

Accumulation of fat around the heart has long been linked to cardiovascular and metabolic disease but until now there hasn’t been a simple way to measure this. A new AI tool has been developed that can quantify these fat deposits from regular MRI images.

A new AI-based system is able to ascertain which facial features are found most attractive by individual people. It can then create computer-generated faces combining those qualities.

Given how long some 3D-printing jobs can take, most people don't sit around and watch the entire process. This means they may miss printing errors, which waste a lot of filament. AIMS, however, reportedly uses AI to spot errors and stop the printer.

A pair of studies are showing how passive smartphone data can be used to predict relapse episodes in schizophrenia patients. The research used machine learning to analyze behavioral data and predict schizophrenic relapses up to one month before they occurred.

A new study has validated the efficacy of a novel AI algorithm designed to deliver accurate MRI results using a quarter of the data of current systems. This innovation promises to speed up MRI scans without upgrades to pre-existing imaging hardware.