Artificial intelligence systems, such as large language models (LLMs) and convolutional neural networks (CNNs), can analyze large amounts of data and rapidly generate desired content or identify meaningful patterns. However, when running on existing hardware, such as smartphones, laptops and tablets, these systems typically consume a large amount of energy.
Over the past decade or so, electronics engineers have been increasingly working on alternative hardware systems that could run AI models more energy efficiently. Many of these systems are neuromorphic, meaning that they are inspired by the structure and functioning of the human brain.
Researchers at Huazhong University of Science and Technology and the Chinese University of Hong Kong recently introduced a new approach for designing neuromorphic computing hardware based on two-dimensional materials. Their proposed strategy, introduced in a paper published in Nature Electronics, was used to develop a chip based on the 2D semiconductor molybdenum disulfide (MoS2) that can reliably run AI algorithms while consuming less power.









