Purdue researchers build human brain-inspired hardware for AI to enable continuous learning
Purdue researchers build human brain-inspired hardware for AI to enable continuous learning
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 specializes 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. 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.
How Does this Chips Work ?
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 center, 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.
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 recognize 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.
“The brains of living beings can continuously learn throughout their lifespan. We have now created an artificial platform for machines to learn throughout their lifespan,” said Shriram Ramanathan, a professor in Purdue University’s School of Materials Engineering who specializes in discovering how materials could mimic the brain to improve computing.
Unlike the brain, which constantly forms new connections between neurons to enable learning, the circuits on a computer chip don’t change. A circuit that a machine has been using for years isn’t any different than the circuit that was originally built for the machine in a factory.
This is a problem for making AI more portable, such as for autonomous vehicles or robots in space that would have to make decisions on their own in isolated environments. If AI could be embedded directly into hardware rather than just running on software as AI typically do, these machines would be able to operate more efficiently.
When the device has more hydrogen near its center, for example, 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.
Through simulations of the experimental data, the Purdue team’s collaborators at Santa Clara University and Portland State University showed that the internal physics of this device creates a dynamic structure for an artificial neural network that is able to more efficiently recognize electrocardiogram patterns and digits compared to static networks. This neural network uses “reservoir computing,” which explains how different parts of a brain communicate and transfer information.
Researchers from The Pennsylvania State University also demonstrated in this study that as new problems are presented, a dynamic network can “pick and choose” which circuits are the best fits for addressing those problems. Since the team was able to build the device using standard semiconductor-compatible fabrication techniques and operate the device at room temperature, Ramanathan believes that this technique can be readily adopted by the semiconductor industry.
“We demonstrated that this device is very robust,” said Michael Park, a Purdue PhD student in materials engineering. “After programming the device over a million cycles, the reconfiguration of all functions is remarkably reproducible,” Park added.
The researchers are working to demonstrate these concepts on large-scale test chips that would be used to build a brain-inspired computer. Experiments at Purdue were conducted at the FLEX Lab and Birck Nanotechnology Center of Purdue’s Discovery Park. The team’s collaborators at Argonne National Laboratory, the University of Illinois, Brookhaven National Laboratory and the University of Georgia conducted measurements of the device’s properties. The research was supported by the U.S. Department of Energy Office of Science, the Air Force Office of Scientific Research and the National Science Foundation.
- Follow Robotics India on Facebook
- Follow Robotics India on Google News
- Follow Robotics India on Twitter
- Follow Robotics India on Instagram
