Researchers at Purdue University have created an artificial platform for machines to help them learn through their lifespans. The researchers aim to make AI more portable by embedding it directly into the hardware, instead of running AI as software, making machines operate more efficiently, especially in isolated environments such as space or autonomous vehicles.
“If we want to build a computer or a machine that is inspired by the brain, then correspondingly, we want to have the ability to continuously program, reprogram and change the chip,” Shriram Ramanathan, a professor in Purdue University’s School of Materials Engineering, said. He specialises in discovering how materials could mimic the brain to improve computing.
Human brains are capable of continuous learning throughout their life spans by forming new neural connections. However, the circuits on a computer chip don’t change.
AIM Daily XO
Join our editors every weekday evening as they steer you through the most significant news of the day, introduce you to fresh perspectives, and provide unexpected moments of joy
The researchers, under the aegis of Ramanathan, built a hardware that can be reprogrammed on-demand using electrical pulses. Ramanathan believes the adaptability will allow the device to take on all functions necessary to build a brain-inspired computer.
The hardware is a small, rectangular device made of a material called perovskite nickelate, which is very sensitive to hydrogen. Applying electrical pulses at different voltages allows the device to shuffle a concentration of hydrogen ions in a matter of nanoseconds, creating states that the researchers found could be mapped out to corresponding functions in the brain. When the device has more hydrogen near its centre, it can act as a neuron, a single nerve cell. With less hydrogen at that location, the device serves as a synapse, a connection between neurons, which is what the brain uses to store memory in complex neural circuits.
Download our Mobile App
Through simulations of the experimental data, the Purdue team’s collaborators at Santa Clara University and Portland State University showed the internal physics of this device creates a dynamic structure for an artificial neural network with the ability to efficiently recognise electrocardiogram patterns and digits compared to static networks. The neural network uses “reservoir computing,” which explains how different parts of a brain communicate and transfer information.
The researchers are working to demonstrate these concepts on large-scale test chips.