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
- Bambu Lab launches PLA Pure filament — New material boasts kid-safe toy certifications and "asbestos-free" talc
- SMI says Nvidia is driving its consumer PCIe 6.0 roadmap, not AMD and Intel — RTX Spark agentic AI platform fuels a hunger for storage bandwidth
- SanDisk Optimus GX Pro 8100 8TB SSD Review — the undisputed king of high-capacity PCIe 5.0 SSDs
- Intel's fab roadmap examined — Arizona, Ohio, Ireland, and the two deadlines deciding 14A process node
- NVIDIA Blackwell Leads on First Agentic AI Infrastructure Benchmark
Informational only. No financial advice. Do your own research.