First Programmable Memristor Computer Aims to Bring AI Processing Down from the Cloud
July 18, 2019 | Michigan State UniversityEstimated reading time: 4 minutes

The memristor array chip plugs into the custom computer chip, forming the first programmable memristor computer. The team demonstrated that it could run three standard types of machine learning algorithms. Image credit: Robert Coelius, Michigan Engineering.
ANN ARBOR—The first programmable memristor computer—not just a memristor array operated through an external computer—has been developed at the University of Michigan.
It could lead to the processing of artificial intelligence directly on small, energy-constrained devices such as smartphones and sensors. A smartphone AI processor would mean that voice commands would no longer have to be sent to the cloud for interpretation, speeding up response time.
“Everyone wants to put an AI processor on smartphones, but you don’t want your cell phone battery to drain very quickly,” said Wei Lu, U-M professor of electrical and computer engineering and senior author of the study in Nature Electronics.
In medical devices, the ability to run AI algorithms without the cloud would enable better security and privacy.
Why Memristors are Good for Machine Learning
The key to making this possible could be an advanced computer component called the memristor. This circuit element, an electrical resistor with a memory, has a variable resistance that can serve as a form of information storage. Because memristors store and process information in the same location, they can get around the biggest bottleneck for computing speed and power: the connection between memory and processor.
This is especially important for machine-learning algorithms that deal with lots of data to do things like identify objects in photos and videos—or predict which hospital patients are at higher risk of infection. Already, programmers prefer to run these algorithms on graphical processing units rather than a computer’s main processor, the central processing unit.
“GPUs and very customized and optimized digital circuits are considered to be about 10-100 times better than CPUs in terms of power and throughput.” Lu said. “Memristor AI processors could be another 10-100 times better.”
GPUs perform better at machine learning tasks because they have thousands of small cores for running calculations all at once, as opposed to the string of calculations waiting their turn on one of the few powerful cores in a CPU.
A memristor array takes this even further. Each memristor is able to do its own calculation, allowing thousands of operations within a core to be performed at once. In this experimental-scale computer, there were more than 5,800 memristors. A commercial design could include millions of them.
Memristor arrays are especially suited to machine learning problems. The reason for this is the way that machine learning algorithms turn data into vectors—essentially, lists of data points. In predicting a patient’s risk of infection in a hospital, for instance, this vector might list numerical representations of a patient’s risk factors.
Then, machine learning algorithms compare these “input” vectors with “feature” vectors stored in memory. These feature vectors represent certain traits of the data (such as the presence of an underlying disease). If matched, the system knows that the input data has that trait. The vectors are stored in matrices, which are like the spreadsheets of mathematics, and these matrices can be mapped directly onto the memristor arrays.
What’s more, as data is fed through the array, the bulk of the mathematical processing occurs through the natural resistances in the memristors, eliminating the need to move feature vectors in and out of the memory to perform the computations. This makes the arrays highly efficient at complicated matrix calculations. Earlier studies demonstrated the potential of memristor arrays for speeding up machine learning, but they needed external computing elements to function.
Wei Lu stands with first author Seung Hwan Lee, an electrical engineering PhD student, who holds the memristor array. Image credit: Robert Coelius, Michigan Engineering
Page 1 of 2
Suggested Items
Specially Developed for Laser Plastic Welding from LPKF
06/25/2025 | LPKFLPKF introduces TherMoPro, a thermographic analysis system specifically developed for laser plastic welding that transforms thermal data into concrete actionable insights. Through automated capture, evaluation, and interpretation of surface temperature patterns immediately after welding, the system provides unprecedented process transparency that correlates with product joining quality and long-term product stability.
Smart Automation: The Power of Data Integration in Electronics Manufacturing
06/24/2025 | Josh Casper -- Column: Smart AutomationAs EMS companies adopt automation, machine data collection and integration are among the biggest challenges. It’s now commonplace for equipment to collect and output vast amounts of data, sometimes more than a manufacturer knows what to do with. While many OEM equipment vendors offer full-line solutions, most EMS companies still take a vendor-agnostic approach, selecting the equipment companies that best serve their needs rather than a single-vendor solution.
Keysight, NTT, and NTT Innovative Devices Achieve 280 Gbps World Record Data Rate with Sub-Terahertz for 6G
06/17/2025 | Keysight TechnologiesKeysight Technologies, Inc. in collaboration with NTT Corporation and NTT Innovative Devices Corporation (NTT Innovative Devices), today announced a groundbreaking world record in data rate achieved using sub-THz frequencies.
Priority Software Announces the New, Game-Changing aiERP
06/12/2025 | Priority SoftwarePriority Software Ltd., a leading global provider of ERP and business management software announces its revolutionary aiERP, leveraging the power of AI to transform business operations.
Breaking Silos with Intelligence: Connectivity of Component-level Data Across the SMT Line
06/09/2025 | Dr. Eyal Weiss, CybordAs the complexity and demands of electronics manufacturing continue to rise, the smart factory is no longer a distant vision; it has become a necessity. While machine connectivity and line-level data integration have gained traction in recent years, one of the most overlooked opportunities lies in the component itself. Specifically, in the data captured just milliseconds before a component is placed onto the PCB, which often goes unexamined and is permanently lost once reflow begins.