This could be especially useful for neuromorphic computing, a field that tries to build computing systems modeled on biological neural networks. It also fits into the broader push toward in-sensor computing, where data is processed at the point of capture rather than being shuttled off to separate processors and memory banks.
For AI vision systems, that could mean hardware capable of filtering, weighting, and temporarily retaining visual information before it ever reaches a conventional processor. A robot, drone, security camera, or autonomous system may not need to preserve every visual signal forever. Some information should matter briefly, some should matter longer, and some should disappear almost immediately.
“This light-sensitive memory with a programmable memory lifetime creates a tunable time window for processing visual and other sensor signals directly where they are detected, a capability that could enable more efficient vision systems and other sensor-based AI technologies,” Cheng said.
The research is still at the device level, so this is not a drop-in replacement for today’s AI accelerators or image sensors. However, it points toward hardware that could make future AI systems less dependent on constantly moving data between sensors, memory, and processors. If scaled successfully, that could help AI devices become faster, more compact, and less power-hungry, particularly in edge systems where energy efficiency matters most.
Follow Tom's Hardware on Google News , or add us as a preferred source , to get our latest news, analysis, & reviews in your feeds.
Etiido Uko is a news contributor for Tom's Hardware covering the latest updates in big tech and the PC industry. He is a mechanical engineer and senior technical writer with over nine years of experience in documentation and reporting. He is deeply passionate about all things engineering and technology, and is an expert in gadgets, manufacturing, robotics, automotive, and aerospace. ","collapsible":{"enabled":true,"maxHeight":250,"readMoreText":"Read more","readLessText":"Read less"}}), "https://slice.vanilla.futurecdn.net/13-4-24/js/authorBio.js"); } else { console.error('%c FTE ','background: #9306F9; color: #ffffff','no lazy slice hydration function available'); } Etiido Uko Social Links Navigation News Contributor Etiido Uko is a news contributor for Tom's Hardware covering the latest updates in big tech and the PC industry. He is a mechanical engineer and senior technical writer with over nine years of experience in documentation and reporting. He is deeply passionate about all things engineering and technology, and is an expert in gadgets, manufacturing, robotics, automotive, and aerospace.
Key considerations
- Investor positioning can change fast
- Volatility remains possible near catalysts
- Macro rates and liquidity can dominate flows
Reference reading
- https://www.tomshardware.com/tech-industry/artificial-intelligence/SPONSORED_LINK_URL
- https://www.tomshardware.com/tech-industry/artificial-intelligence/researchers-build-brain-like-memory-device-for-ai-sensors-that-may-improve-energy-efficiency-phototransistor-device-combines-light-sensing-memory-and-processing-to-cut-data-movement#main
- https://www.tomshardware.com/subscription
- US energy regulator to order grid operators to expedite AI data center applications — says projects should bring their own power or cut usage during high demand
- HPE AI Factory With NVIDIA Expands for the Era of Agents
- First official details of AMD's next-gen 'Mustang Peak' Threadripper CPUs come into view — chips feature DDR5, PCIe 6.0, and a new socket
- For Robotaxis, Safety Must Be Built In, Not Bolted On
- AMD silently removes memory encryption from consumer Ryzen CPUs, leaving users unaware that they may be vulnerable — security feature vanishes after newer AGESA
Informational only. No financial advice. Do your own research.