From lab to life: Atomic-scale memristors pave the way for brain-like AI and next-generation computing power
- Memristors to bring brain-like computing to AI systems
- Atomically tunable devices provide low-power AI processing
- Neuromorphic circuits open new possibilities for artificial intelligence
A new frontier in semiconductor technology could be closer than ever following the development of atomically tunable ‘memristors’, advanced memory resistors that emulate the neural network of the human brain.
With funding from the National Science Foundation’s Future of Semiconductors (FuSe2) program, this initiative aims to create devices that enable neuromorphic computing – a next-generation approach designed for fast, energy-efficient processing that mimics the brain’s ability to learn and adapt. .
At the heart of this innovation is the creation of ultra-thin memory devices with atomic-scale control, potentially revolutionizing AI by allowing memristors to act as artificial synapses and neurons. These devices have the potential to significantly improve computing power and efficiency and open up new possibilities for artificial intelligence applications, while training a new generation of semiconductor technology experts.
Neuromorphic computing challenges
The project focuses on solving one of the most fundamental challenges in modern computing: achieving the precision and scalability needed to bring brain-inspired AI systems to life.
To develop energy-efficient, high-speed networks that function like the human brain, memristors are the key components. They can store and process information simultaneously, making them particularly suitable for neuromorphic circuits where they can facilitate the kind of parallel data processing seen in biological brains, potentially overcoming limitations in traditional computer architectures.
The joint research effort between the University of Kansas (KU) and the University of Houston led by Judy Wu, a distinguished professor of physics and astronomy at KU, is supported by a $1.8 million grant from FuSe2.
Wu and her team have developed a method to achieve thicknesses of less than 2 nanometers in memory devices, with film layers approaching an astonishing thickness of 0.1 nanometers – about 10 times thinner than the average nanometer scale.
These developments are crucial for future semiconductor electronics, as they enable the creation of devices that are both extremely thin and capable of precise functionality, with uniformity over a large surface area. The research team will also use a co-design approach that integrates material design, manufacturing and testing.
In addition to the scientific objectives, the project also has a strong focus on workforce development. Recognizing the growing need for skilled professionals in the semiconductor industry, the team has designed an educational outreach component led by experts from both universities.
“The overarching goal of our work is to develop atomically ‘tunable’ memristors that can act as neurons and synapses on a neuromorphic circuit. By developing this circuit, we aim to enable neuromorphic computing. This is the primary focus of our research,” said Wu.
“We want to mimic how our brains think, calculate, make decisions and recognize patterns – essentially everything the brain does at high speed and high energy efficiency.”