Jülich, August 15, 2022 – They are many times faster than flash memory and consume significantly less energy: memristive memory cells could revolutionize the energy efficiency of neuromorphic computers. In these computers, which are modeled after the way the human brain works, memristive cells function as artificial synapses. Countless groups around the world are working on using similar neuromorphic circuits – but often with a lack of understanding of how they work and with faulty models. Jülich’s researchers have now summarized the physical principles and models in an extensive review article in the renowned journal Advances in Physics.
Certain tasks – such as recognizing patterns and language – are performed very efficiently by a human brain and require only about one ten-thousandth of the energy of a conventional, so-called “von Neumann” computer. One of the reasons lies in the structural differences: in a von Neumann architecture, there is a clear separation between memory and processor, which requires constant movement of large amounts of data. This takes time and energy – the so-called von Neumann bottleneck. In the brain, the computational processing takes place directly in the data memory and the biological synapses simultaneously perform the tasks of memory and processor.
At Jülich, scientists have been working for more than 15 years on special data storage devices and components that could have similar properties to the synapses in the human brain. So-called memristive memory devices, also known as memristors, are considered to be extremely fast, energy-saving and can be miniaturized to the nearest nanometer. The operation of memristive cells is based on a very special effect: their electrical resistance is not constant, but can be changed and reset by applying an external voltage, theoretically continuous. The change in resistance is controlled by the movement of oxygen ions. As these move out of the semiconducting metal oxide layer, the material becomes more conductive and the electrical resistance decreases. This change in resistance can be used to store information.
The processes that can take place in cells are very complex and vary depending on the material system. Three researchers from the Jülich Peter Grünberg Institute – Prof. Regina Dittmann, Dr. Stephan Menzel and Prof. Rainer Waser – therefore pooled their research results in a detailed review article, “Nanoionic memristive phenomena in metal oxides: the valence change mechanism”. They explain in detail the various physical and chemical effects in memristors and shed light on the influence of these effects on the switching properties of memristive cells and their reliability.
“If you look at the current research activities in the field of neuromorphic memristor circuits, they are often based on empirical approaches to materials optimization,” says Rainer Waser, director of the Peter Grünberg Institute. “Our goal with our review article is to give researchers something to work with to enable insight-driven materials optimization.” The team of authors worked for ten years on the approximately 200-page article and of course had to keep incorporating the knowledge.
“The analogous functioning of memristive cells required for their use as artificial synapses is not the normal case. Usually there are sudden resistance jumps, generated by the mutual amplification of ionic motion and Joule heat,” explains Regina Dittmann of the Peter Grünberg Institute from. . “In our review article, we give researchers the necessary insight into how to change the dynamics of the cells to enable an analog mode of operation.”
“You see over and over that groups simulate their memristor circuits with models that don’t take into account the high dynamics of the cells at all. Those circuits will never work.” said Stephan Menzel, who leads modeling activities at the Peter Grünberg Institute and has developed powerful compact models that are now in the public domain (www.emrl.de/jart.html). “In our review article, we provide the basics that are extremely useful for the correct use of our compact models.”
Neuromorphic Computing Roadmap
The “Roadmap of Neuromorphic Computing and Engineering”, published in May 2022, shows how neuromorphic computing can help reduce the massive energy consumption of IT worldwide. In it, researchers from the Peter Grünberg Institute (PGI-7), together with leading experts in the field, bundled the various technological possibilities, computational approaches, learning algorithms and application areas.
According to the study, applications in the field of artificial intelligence, such as pattern recognition or speech recognition, are likely to benefit in a special way from the use of neuromorphic hardware. This is because – much more than classical computer numerical operations – they are based on the shifting of large amounts of data. Memristive cells make it possible to process these gigantic data sets directly in memory without having to transport them back and forth between processor and memory. This could reduce the energy efficiency of artificial neural networks by orders of magnitude.
Memristive cells can also be linked together to form high-density matrices that allow neural networks to learn locally. This so-called edge computing therefore shifts calculations from the data center to the factory floor, the vehicle or the home of people who need care. For example, processes can be monitored and checked or rescue measures are taken without data being sent via a cloud. “This achieves two things at once: you save energy while at the same time keeping personal and security-relevant data on the site,” says Prof. Dittmann, who played a key role as editor in creating the roadmap.
Regina Dittmann, Stephan Menzel, Rainer Waser: “Nanoionic Memristive Phenomena in Metal Oxides: The Valence Change Mechanism”, Advances in Physics (2022)
DV Christensen, R. Dittmann, B. Linares-Barranco, A. Sebastian, M. Le Gallo, A. Redaelli, S. Slesazeck, T. Mikolajick, S. Spiga, S. Menzel, I. Valov, G. Milano, C. Ricciardi, S.-J. Liang, F. Miao, M. Lanza, TJ Quill, ST Keene, Alberto Salleo, J. Grollier, D. Markovic, A. Mizrahi, P. Yao, J. Joshua Yang, G. Indiveri, JP Strachan, S Datta, E. Vianello, A. Valentian, J. Feldmann, X. Li, W. HP Pernice, H. Bhaskaran, S. Furber, E. Neftci, F. Scherr, W. Maass, S. Ramaswamy, J. Tapson, P Panda, Y. Kim, G. Tanaka, S. Thorpe, C. Bartolozzi, T. A Cleland, C. Posch, S.-C.Liu, G. Panuccio, M. Mahmud, AN Mazumder, M Hosseini, T Mohsenin, E. Donati, S. Tolu, R. Galeazzi, ME Christensen, S. Holm, D. Ielmini, and Nini Pryds, “2022 roadmap on neuromorphic computing and engineering”, Accepted for publication in Neuromorphic Computing and Engineering (2022) ,
Advances in Physics
Subject of research
Nanoionic Memristive Phenomena in Metal Oxides: The Valence Change Mechanism
Article publication date
#Synapses #model #solidstate #memory #neuromorphic #circuits