Toggle light / dark theme

A new brain-inspired architecture could improve how computers handle data and advance AI

General interest.


IBM researchers are developing a new computer architecture, better equipped to handle increased data loads from artificial intelligence. Their designs draw on concepts from the human brain and significantly outperform conventional computers in comparative studies. They report on their recent findings in the Journal of Applied Physics.

Today’s computers are built on the von Neumann architecture, developed in the 1940s. Von Neumann computing systems feature a central processer that executes logic and arithmetic, a memory unit, storage, and input and output devices. Unlike the stovepipe components in conventional computers, the authors propose that brain-inspired computers could have coexisting processing and memory units.

Abu Sebastian, an author on the paper, explained that executing certain in the computer’s memory would increase the system’s efficiency and save energy.

The Next Social Networks Could Be Brain-to-Brain

It might already feel like social media is taking up too much of our mental space, but just wait until it’s literally inside of our brains.

Physicists and neuroscientists have developed the world’s first “brain-to-brain” network, using electroencephalograms (EEGs), which record electrical activity in the brain, and transcranial magnetic stimulation (TMS), which can transmit information into the brain, to allow people to communicate directly with each other’s brains — a new and thrilling (and a little terrifying?) example of science fiction brought to life.

Researchers at the University of Washington in Seattle announced last week that they successfully used their interface, which they call BrainNet, to have a small group of people play a collaborative “Tetris-like” game — with their minds.

Incredible strength of ‘nuclear pasta’ revealed in new simulations

Researchers from Indiana University and the California Institute of Technology say the new simulations could help us better understand major astrophysical phenomena, such as gravitational waves.

‘The strength of the neutron star crust, especially the bottom of the crust, is relevant to a large number of astrophysics problems, but isn’t well understood,’ says Matthew Caplan, a postdoctoral research fellow at McGill University.

Neutron stars are the product of supernovas, and are extremely dense.

/* */