Science, Space and Technology News 2024
Artificial neural networks could soon process time-dependent data more efficiently with the development of a tunable memristor. This technology, detailed in a University of Michigan-led study, could significantly reduce AI energy consumption.
Credit: SciTechDaily.com In the brain, timekeeping is done with neurons that relax at different rates after receiving a signal; now memristors—hardware analogs of neurons—can do that too. Artificial neural networks may soon be able to process time-dependent information, such as audio and video data, more efficiently. The first memristor with a ‘relaxation time’ that can be tuned is reported today in Nature Electronics, in a study led by the University of Michigan.compared to today’s graphical processing units. Already, AI is projected to account for about half a percent of the world’s total electricity consumption in 2027, and that has the potential to balloon as more companies sell and use AI tools. “Right now, there’s a lot of interest in AI, but to process bigger and more interesting data, the approach is to increase the network size. That’s not very efficient,” said Wei Lu, the James R. Mellor Professor of Engineering at U-M and co-corresponding author of the study with John Heron, U-M associate professor of materials science and engineering.The problem is that GPUs operate very differently from the artificial neural networks that run the AI algorithms—the whole network and all its interactions must be sequentially loaded from the external memory, which consumes both time and energy. In contrast, memristors offer energy savings because they mimic key aspects of the way that both artificial and biological neural networks function without external memory. To an extent, the memristor network can embody the artificial neural network.“We anticipate that our brand-new material system could improve the energy efficiency of AI chips six times over the state-of-the-art material without varying time constants,” said Sieun Chae, a recent U-M Ph.D. graduate in materials science and engineering and co-first-author of the study with Sangmin Yoo, a recent U-M PhD graduate in electrical and computer engineering. In a biological neural network, timekeeping is achieved through relaxation. Each neuron receives electrical signals and sends them on, but it isn’t a guarantee that a signal will move forward. Some threshold of incoming signals must be reached before the neuron will send its own, and it has to be met in a certain amount of time. If too much time passes, the neuron is said to relax as the electrical energy seeps out of it. Having neurons with different relaxation times in our neural networks helps us understand sequences of events.Memristors operate a little differently. Rather than the total presence or absence of a signal, what changes is how much of the electrical signal gets through. Exposure to a signal reduces the resistance of the memristor, allowing more of the next signal to pass. In memristors, relaxation means that the resistance rises again over time. While Lu’s group had explored building relaxation time into memristors in the past, it was not something that could be systematically controlled. But now, Lu and Heron’s team have shown that variations on a base material can provide different relaxation times, enabling memristor networks to mimic this timekeeping mechanism.The team built the materials on the superconductor YBCO, made of yttrium, barium, carbon and oxygen. It has no electrical resistance at temperatures below -292, but they wanted it for its crystal structure. It guided the organization of the magnesium, cobalt, nickel, copper and zinc oxides in the memristor material. Heron calls this type of oxide, an entropy-stabilized oxide, the “kitchen sink of the atomic world”—the more elements they add, the more stable it becomes. By changing the ratios of these oxides, the team achieved time constants ranging from 159 to 278 nanoseconds, or trillionths of a second. The simple memristor network they built learned to recognize the sounds of the numbers zero to nine. Once trained, it could identify each number before the audio input was complete.These memristors were made through an energy-intensive process because the team needed perfect crystals to precisely measure their properties, but they anticipate that a simpler process would work for mass manufacturing. “So far, it’s a vision, but I think there are pathways to making these materials scalable and affordable,” Heron said. “These materials are earth-abundant, nontoxic, cheap and you can almost spray them on.” Reference: “Efficient data processing using tunable entropy-stabilized oxide memristors” by Sangmin Yoo, Sieun Chae, Tony Chiang, Matthew Webb, Tao Ma, Hanjong Paik, Yongmo Park, Logan Williams, Kazuki Nomoto, Huili G. Xing, Susan Trolier-McKinstry, Emmanouil Kioupakis, John T. Heron and Wei D. Lu, 20 May 2024,The research was funded by the National Science Foundation. It was done in partnership with researchers at the University of Oklahoma, Cornell University and Pennsylvania State University. The device was built in the Lurie Nanofabrication Facility and studied at the Michigan Center for Materials Characterization. Lu is also a professor of electrical and computer engineering and materials science and engineering. Chae is now an assistant professor of electrical engineering and computer science at Oregon State University.SciTechDaily: Home of the best science and technology news since 1998. Keep up with the latest scitech news via email or social media.OSIRIS-APEX, a NASA spacecraft, successfully navigated its closest approach to the Sun, exceeding design expectations and demonstrating robust engineering by protecting its sensitive components. Innovative…
United States Latest News, United States Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
New iPad Pro Features Breakthrough OLED, New Chip, and Thinner ChassisApple has debuted new iPad Pro models, complete with Tandem OLED display tech and brand-new Apple M4 chips.
Read more »
Designer peptoids mimic nature's helicesNature is filled with extraordinarily precise molecular shapes that fit together like a hand in glove. Proteins, for example, can assemble into a wide variety of well-defined shapes that grant them their function.
Read more »
Brain 'assembloids' mimic human blood-brain barrierMajor advance promises to accelerate the understanding and improved treatment of a wide range of brain disorders, including stroke, cerebral vascular disorders, brain cancer, Alzheimer's disease, Huntington disease, Parkinson's disease, and other neurodegenerative conditions.
Read more »
Breakthrough discovery uses engineered surfaces to shed heatSplash a few drops of water on a hot pan and if the pan is hot enough, the water will sizzle and the droplets of water seem to roll and float, hovering above the surface. The temperature at which this phenomenon, called the Leidenfrost effect, occurs is predictable, usually happening above 230 degrees Celsius.
Read more »
Quantum Leap: Atom Interference and a Breakthrough in Boson SamplingScience, Space and Technology News 2024
Read more »
Webb Telescope’s Breakthrough: First Atmospheric Discovery on a Rocky Super-EarthScience, Space and Technology News 2024
Read more »