↓ Pull down to refresh stories
Write Login VI Store
News Devices Apr 5, 2026, 9:33 PM
Emerging

Researchers train living rat neurons to perform real-time AI computations

A team at Tohoku University and Future University Hakodate in Japan trained cultured rat cortical neurons to autonomously generate complex temporal signals using a real-time machine learning framework, according to a study published March 12 in the journal Proceedings of the National Academy of Sciences . The researchers integrated the living neurons with high-density microelectrode arrays and microfluidic devices, creating a closed-loop reservoir computing system that learned to produce periodic and chaotic waveforms without any external input. This piece sits on 1 source layers, but the real value is showing why the story should not be skimmed past too quickly.

A team at Tohoku University and Future University Hakodate in Japan trained cultured rat cortical neurons to autonomously generate complex temporal signals using a real-time machine learning framework, according to a study published March 12 in the journal Proceedings of the National Academy of Sciences . The researchers integrated the living neurons with high-density microelectrode arrays and microfluidic devices, creating a closed-loop reservoir computing system that learned to produce periodic and chaotic waveforms without any external input. The signal is strong enough to deserve attention, but it still needs to be read as something developing rather than fully settled.

Quang Huy Devices and Digital Infrastructure Editor
Emerging The topic has initial corroboration, but the newsroom is still waiting on stronger confirmation.
Reference image for: Researchers train living rat neurons to perform real-time AI computations
Reference image from Tom's Hardware. Tom's Hardware

A team at Tohoku University and Future University Hakodate in Japan trained cultured rat cortical neurons to autonomously generate complex temporal signals using a real-time machine learning framework, according to a study published March 12 in the journal Proceedings of the National Academy of Sciences . The researchers integrated the living neurons with high-density microelectrode arrays and microfluidic devices, creating a closed-loop reservoir computing system that learned to produce periodic and chaotic waveforms without any external input. The system recorded spike trains from the neurons across a 26,400-electrode array with a 17.5-micrometer pitch, filtered them into continuous signals, and decoded an output through a linear readout layer. Tom's Hardware is the main source layer for now, and the rest should be read as a signal that is still widening. On the device side, the useful angle is whether a technical change actually alters feel, lifespan, or upgrade cost in real use.

Advertising slot

Patrick Tech Store Accounts, tools, and software now available in the store This slot is temporarily dedicated to the Patrick Tech ecosystem.

What is happening now

A team at Tohoku University and Future University Hakodate in Japan trained cultured rat cortical neurons to autonomously generate complex temporal signals using a real-time machine learning framework, according to a study published March 12 in the journal Proceedings of the National Academy of Sciences . Tom's Hardware form the main source layer behind the core facts in this piece.

Where the sources line up

Tom's Hardware is the main source layer for now, and the rest should be read as a signal that is still widening. The researchers integrated the living neurons with high-density microelectrode arrays and microfluidic devices, creating a closed-loop reservoir computing system that learned to produce periodic and chaotic waveforms without any external input. Tom's Hardware form the main source layer behind the core facts in this piece.

Advertising slot

Patrick Tech Store Accounts, tools, and software now available in the store This slot is temporarily dedicated to the Patrick Tech ecosystem.

The details worth keeping

The system recorded spike trains from the neurons across a 26,400-electrode array with a 17.5-micrometer pitch, filtered them into continuous signals, and decoded an output through a linear readout layer. On the device side, the useful angle is whether a technical change actually alters feel, lifespan, or upgrade cost in real use.

Why this matters most

The signal is strong enough to deserve attention, but it still needs to be read as something developing rather than fully settled. With 1 source layers on the table, the part worth reading most closely is where firm facts meet the market's early reaction. That output was then fed back to the neurons as electrical stimulation, completing a feedback loop that cycled roughly every 333 milliseconds.

What to watch next

The next readout is price, device coverage, and whether the change feels real once the hardware reaches users. Patrick Tech Media will keep checking rollout speed, user reaction, and how Tom's Hardware update the next pieces. From 1 early signals, the piece keeps 1 references that are useful for locking the main details in place.

Source notes

Related stories