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

Meet Ari, the Smart Bike that Helps you Catch Green Lights

As more bikes take to the city streets than ever, researchers at RMIT have designed Ari, a smart e-bike that could help riders cruise the ‘green wave’.

Continue reading

Overcoming Challenges in Building Enterprise AI Assistants

A team of researchers from IBM Research AI and AI Horizons Network-partner the University of Michigan published the papers “A Large-Scale Corpus for Conversation Disentanglement” and “Learning End-to-End Goal-Oriented Dialog with Maximal User Task Success and Minimal Human Agent Use” at ACL 2019. This work address two main challenges in building enterprise AI assistants.

Continue reading

Four Papers Advance Computational Argumentation in IBM’s Project Debater

The latest work on computational argumentation from the IBM Project Debater research team group is being presented at the ACL 2019 conference. Three papers will be presented at the main conference and one more paper will be presented in the co-located Argument Mining Workshop.

Continue reading