Artificial intelligence (AI) can require software running on thousands of computers - the energy that three nuclear power plants produce in one hour. A team of engineers has created hardware that can learn skills using a type of AI that currently runs on software platforms. Sharing intelligence features between hardware and software would offset the energy needed for using AI in more advanced applications such as self-driving cars or discovering drugs.
As AI penetrates more of daily life, a heavy reliance on software with massive energy needs is not sustainable. If hardware and software could share intelligence features, an area of silicon might be able to achieve more with a given input of energy.
Software uses tree-like memory to organize information into various “branches,” making that information easier to retrieve when learning new skills or tasks. The strategy is inspired by how the human brain categorizes information and makes decisions. Artificial “tree-like” memory was demonstrated in a piece of potential hardware at room temperature. In the past, this kind of memory was only observed in hardware at temperatures that are too low for electronic devices. The hardware is made of quantum material that has properties that cannot be explained by classical physics.
The team introduced a proton to a quantum material called neodymium nickel oxide. They discovered that applying an electric pulse to the material moves around the proton. Each new position of the proton creates a different resistance state, which creates an information storage site called a memory state. Multiple electric pulses create a branch made up of memory states. Thousands of memory states can be built up in the material by taking advantage of quantum mechanical effects.
Through simulations of the properties discovered in this material, the team showed that the material is capable of learning the numbers 0 through 9. The ability to learn numbers is a baseline test of artificial intelligence. The demonstration of these trees at room temperature in a material is a step toward showing that hardware could offload tasks from software. The material might also help create a way for humans to more naturally communicate with AI.