Researchers have developed a new method called “linear-complexity multiplication” (ℒ-Mul) to make calculations in artificial intelligence more efficient. The method replaces complex multiplications with simpler additions, according to Jason Hickey and his team at the Google AI Research Center in Accra.
The researchers showed that ℒ-Mul achieves the same accuracy as traditional methods for language models such as Llama and Mistral, but requires significantly less computing power. In tests of various AI tasks such as text comprehension and mathematical reasoning, ℒ-Mul performed as well as or better than previous methods. The researchers see great potential in making AI systems more energy efficient and enabling them to run on devices with limited computing power.
Their results are available here at arxiv.org.
Sources: Hacker News, Tom’s Hardware