First Programmable Memristor Computer Aims to Bring AI Processing Down from the Cloud
July 18, 2019 | Michigan State UniversityEstimated reading time: 4 minutes
To build the first programmable memristor computer, Lu’s team worked with associate professor Zhengya Zhang and professor Michael Flynn, both of electrical and computer engineering at U-M, to design a chip that could integrate the memristor array with all the other elements needed to program and run it. Those components included a conventional digital processor and communication channels, as well as digital/analog converters to serve as interpreters between the analog memristor array and the rest of the computer.
Lu’s team then integrated the memristor array directly on the chip at U-M’s Lurie Nanofabrication Facility. They also developed software to map machine learning algorithms onto the matrix-like structure of the memristor array.
The team demonstrated the device with three bread-and-butter machine learning algorithms:
- Perceptron, which is used to classify information. They were able to identify imperfect Greek letters with 100% accuracy
- Sparse coding, which compresses and categorizes data, particularly images. The computer was able to find the most efficient way to reconstruct images in a set and identified patterns with 100% accuracy
- Two-layer neural network, designed to find patterns in complex data. This two-layer network found commonalities and differentiating factors in breast cancer screening data and then classified each case as malignant or benign with 94.6% accuracy.
There are challenges in scaling up for commercial use—memristors can’t yet be made as identical as they need to be and the information stored in the array isn’t entirely reliable because it runs on analog’s continuum rather than the digital either/or. These are future directions of Lu’s group.
Lu plans to commercialize this technology. The study is titled, “A fully integrated reprogrammable memristor–CMOS system for efficient multiply–accumulate operations.” The research is funded by the Defense Advanced Research Projects Agency, the center for Applications Driving Architectures (ADA), and the National Science Foundation.
Page 2 of 2Suggested Items
Universal Avionics Connected FMS Certified on Part 25 Aircraft Models
04/01/2025 | Universal AvionicsUniversal Avionics (UA), an Elbit Systems company, today announces that FAA certification has been achieved for the installation of its Wi-Fi-enabled Flight Management System (FMS) on Part 25 aircraft models. The Approved Model List Supplemental Type Certificate (AML STC) serves as the foundation for the deployment of Universal’s Connected Avionics onto aircraft.
L3Harris Completes Sale of Commercial Aviation Solutions Business to TJC for $800 Million
03/31/2025 | BUSINESS WIREL3Harris Technologies has completed the previously announced sale of its Commercial Aviation Solutions (CAS) business to an affiliate of TJC L.P. for $800 million. The entire $800 million cash purchase price was paid to L3Harris at the closing of the transaction.
Koh Young Presenting on Real-Time Process Optimization at SEMI Heartland 2025
03/25/2025 | Koh YoungKoh Young, the global leader in True 3D measurement-based inspection and metrology solutions, is pleased to announce that Luis Rivera, MES Team Leader at Koh Young America, will speak at SEMIEXPO Heartland 2025, taking place March 31 to April 2 in Indianapolis, Indiana at the Indiana Convention Center.
Dr. Thomas Marktscheffel of ASMPT Honored for his Work on Open Interfaces
03/25/2025 | ASMPTDr. Thomas Marktscheffel, Director Product Management Software Solutions at ASMPT, was honored by the IPC at this year's IPC APEX EXPO in Anaheim, California, for his many years of commitment to the organization. The non-proprietary interface standards he helped develop form the basis for ASMPT’s intelligent factory concept.
New Power Management Chips from TI Maximize Protection, Density and Efficiency for Modern Data Centers
03/24/2025 | Texas InstrumentsTexas Instruments (TI) debuted new power-management chips to support the rapidly growing power needs of modern data centers. As the adoption of high-performance computing and artificial intelligence (AI) increases, data centers require more power-dense and efficient solutions.