In a groundbreaking advancement set to revolutionize artificial intelligence and computing, researchers from the Indian Institute of Science (IISc) have developed a “brain on a chip” technology. This innovation can store and process data in 16,500 different states within a molecular film, far surpassing traditional binary computing systems.

The study, published in the journal *Nature*, was led by Sreetosh Goswami, along with colleagues from IISc’s Centre for Nano Science and Engineering. Collaborators from Texas A&M University and the University of Limerick contributed to crucial simulation and modeling efforts.

Unlike conventional computing systems that rely on binary processing, this neuromorphic—or brain-inspired—technology mimics the human brain by learning from its environment. Such systems could transform AI by making complex tasks, like training large language models (LLMs) such as ChatGPT, possible on personal devices like laptops and smartphones. The development addresses significant challenges in AI hardware and energy efficiency.

Designed by Prof. Sreebrata Goswami, the molecular system processes and stores data using ion movement, creating what the team calls a “molecular diary” that mimics brain-like functions with enhanced energy efficiency and compactness.