AI Hardware

Steering Material Scientists to Better Memory Devices

Share this post:

Ideally, next-generation AI technologies should understand all our requests and commands, extracting them from a huge background of irrelevant information, in order to rapidly provide relevant answers and solutions to our everyday needs. Making these “smart” AI technologies pervasive—in our smartphones, our homes, and our cars—will require energy-efficient AI hardware, which we at IBM Research plan to build around novel and highly capable analog memory devices.

In a recent paper published in Journal of Applied Physics, our IBM Research AI team established a detailed set of guidelines that emerging nano-scaled analog memory devices will need to satisfy in order to enable such energy-efficient AI hardware accelerators.

We had previously shown, in a Nature paper published in June 2018, that training a neural network using highly parallel computation within dense arrays of memory devices such as phase-change memory is faster and consumes less power than using a graphics processing unit (GPU).

Graphical representation of a crossbar array, where different memory devices serve in different roles

Graphical representation of a crossbar array, where different memory devices serve in different roles

The advantage of our approach comes from implementing each neural network weight with multiple devices, each serving in a different role. Some devices are mainly tasked with memorizing long-term information. Other devices are updated very rapidly, changing as training images (such as pictures of trees, cats, ships, etc.) are shown, and then occasionally transferring their learning to the long-term information devices. Although we introduced this concept in our Nature paper using existing devices (phase change memory and conventional capacitors), we felt there should be an opportunity for new memory devices to perform even better, if we could just identify the requirements for these devices.

In our follow-up paper, just published in Journal of Applied Physics, we were able to quantify the device properties that these “long-term information” and “fast-update” devices would need to exhibit. Because our scheme divides tasks across the two categories of devices, these device requirements are much less stringent—and thus much more achievable—than before.  Our work provides a clear path for material scientists to develop novel devices for energy-efficient AI hardware accelerators based on analog memory.

The team (L-R): Sidney Tsai, Geoffrey Burr, Bob Shelby, Pritish Narayanan, Stefano Ambrogio


Perspective on training fully connected networks with resistive memories: Device requirements for multiple conductances of varying significance. Giorgio Cristiano, Massimo Giordano, Stefano Ambrogio, Louis P. Romero, Christina Cheng, Pritish Narayanan, Hsinyu Tsai, Robert M. Shelby, and Geoffrey W. Burr.  Journal of Applied Physics 124, 151901 (2018). doi:10.1063/1.5042462

Research Staff Member, IBM Research

More AI Hardware stories

Fine-grained visual recognition for mobile AR technical support

Our team of researchers recently published paper “Fine-Grained Visual Recognition in Mobile Augmented Reality for Technical Support,” in IEEE ISMAR 2020, which outlines an augmented reality (AR) solution that our colleagues in IBM Technology Support Services use to increase the rate of first-time fixes and reduce the mean time to recovery from a hardware disruption.

Continue reading

Unlocking the Potential of Today’s Noisy Quantum Computers for OLED Applications

Scientists at Mitsubishi Chemical, a member of the IBM Q Hub at Keio University in Japan, reached out to our team about experimenting with new approaches to error mitigation and novel quantum algorithms to address these very challenges. In the new arXiv preprint, “Applications of Quantum Computing for Investigations of Electronic Transitions in Phenylsulfonyl-carbazole TADF Emitters,” we – along with collaborators at Keio University and JSR - describe quantum computations of the “excited states,” or high energy states, of industrial chemical compounds that could potentially be used in the fabrication of efficient organic light emitting diode (OLED) devices.

Continue reading

Using machine learning to solve a dense hydrogen conundrum

Hydrogen is the simplest element in the universe, yet its behavior in extreme conditions such as very high pressure and temperature is still far from being well understood. Dense hydrogen constitutes the bulk of the content of giant gas planets and brown dwarf stars and it’s a material of interest for both fundamental physics and […]

Continue reading