Sieun Chae from Oregon State University has pioneered a new AI chip that enhances energy efficiency by six times using a novel material system. This breakthrough aims to cut down AI’s hefty energy consumption by mimicking the integrated processing methods of biological neural networks. Credit: SciTechDaily.com
As the use of artificial intelligence soars, so does the amount of energy it requires. Projections show artificial intelligence accounting for half a percent of global energy consumption by 2027 – using as much energy annually as the entire country of the Netherlands. The chips feature components called memristors – short for memory resistors. Most memristors are made from a simple material system composed of two elements, but the ones in this study feature a new material system known as entropy-stabilized oxides, or ESOs. More than a half-dozen elements comprise the ESOs, allowing their memory capabilities to be finely tuned.