Researchers at Surrey University have demonstrated proof-of-concept for using their multimodal transistor (MMT) in artificial neural networks that mimic the human brain.
According to the university, the progress marks an important step towards using thin film transistors as artificial intelligence hardware and advances edge computing, with the prospect of reducing power requirements and improving efficiency, rather than relying solely on computer chips.
The MMT, first reported by Surrey researchers in 2020, would overcome longstanding challenges associated with transistors and perform the same operations as more complex circuits. This latest study, published in Scientific Reports, uses mathematical modeling to prove the concept of using MMTs in artificial intelligence systems.
Using measured and simulated transistor data, the researchers show that well-designed multimodal transistors can operate robustly as rectified linear unit-type (ReLU) activations in artificial neural networks, achieving practically identical classification accuracy as pure ReLU implementations.
Surrey student’s discovery could improve smart electronics
They used measured and simulated MMT data to train an artificial neural network to identify handwritten numbers and compared the results with the software’s built-in ReLU. The results confirmed the potential of MMT devices for thin film decision and classification circuits. The same approach could be used in more complex AI systems.
The research was led by Surrey student Isin Pesch, who worked on the project during the final research module of her BEng (Hons) in Electronic Engineering with Nanotechnology.
“There is a strong need for technological improvements to support the growth of low-cost, large-scale electronics that have been shown to be used in artificial intelligence applications,” Pesch said in a statement. “Thin-film transistors play a role in enabling high processing power with low resource consumption. We can now see that MMTs, a unique type of thin film transistor, invented to [Surrey University], have the reliability and uniformity needed to fulfill this role.”
