Current von Neumann style computing is energy inefficient and bandwidth limited as information is physically shuttled via electrons between processor, short-term non-volatile memory, and long-term storage. Biologically inspired neuromorphic computing, with its inherent autonomous learning capabilities and much lower power requirements based on analog processing, is seen as an avenue for overcoming these limitations. The development of nanoelectronic “memory resistors,” or memristors, is essential to neuromorphic architectures as they allow logic-based elements for information processing to be combined directly with nonvolatile memory for efficient emulation of neurons and synapses found in the brain. Memristors are typically composed of a switchable material with nonlinear hysteretic behavior sandwiched between two conducting encoding elements. The design, dynamic control, scaling, and fundamental understanding of these materials is essential for establishing memristive devices.
The Frontiers in Memristive Materials for Neuromorphic Processing Applications workshop took place on February 28, 2020, in Washington, D.C. (see Appendix B). The National Academies of Sciences, Engineering, and Medicine’s Board on Physics and Astronomy (BPA) organized, planned, and conducted the workshop under the auspices of its Condensed Matter and Materials Research Committee (CMMRC). The goal of the workshop is to explore the state-of-the-art in the materials fundamentally underlying memristor technologies: their science, their mechanisms, and their functional imperatives to realize neuromorphic com-
puting machines. CMMRC recruited expert researchers on memristive materials1 for neuromorphic applications representing academia, industry, and government agencies to present plenaries. Attendees gathered in person at National Academies facilities and via a web livestream.
CMMRC Planning Committee Chair Leslie Momoda, HRL Laboratories, opened the workshop, thanking CMMRC’s sponsors, the U.S. Department of Energy and the National Science Foundation, and delivered welcoming remarks outlining the workshop’s context and purpose. Dr. Momoda noted that so far, materials development has not been a significant contributor to the information revolution. However, the situation may change. There is a need to significantly improve the energy efficiency in the computing and information processing systems in the foreseeable future—in autonomous systems and new computing architectures for advanced processing and decisional systems, for example. This presents an opportunity to consider the contributions and importance of materials development to meet these needs.
By soliciting input from the expert presenters and audience members, the workshop was an opportunity to highlight key challenges, opportunities, and issues in the relevant fields. In particular, Dr. Momoda expected that the workshop would help understanding of the current state and future potential of newer memristive materials technologies to achieve energy-efficient neuromorphic computing and to elicit new directions and thinking that could shape future research programs in this area.
The workshop was unclassified and open to the public. These proceedings provide a condensed summary of the presentations and discussion based on recordings, presentation materials, and transcripts.
1 In very general terms, memristor materials are materials whose state, including but not limited to resistance, depends on the cumulative effect of the voltage placed on them, or current passed through them, over time.