Researchers at the North Carolina-based Duke University revealed a new artificial intelligence system that can set new models for future interactions among the different complex variables in bacteria cultures. Their algorithms are generalizable to many kinds of biological systems, the German News Agency reported.
According to the Phys.org website, the research team has managed to devise a machine learning approach to predict the circular patterns between complex variables in the biological circuit in a bacterial culture. The system worked 30,000 times faster than the existing computational model.
The website cited Lingchong You, professor of biomedical engineering at Duke, as saying: "This work was inspired by Google showing that neural networks could learn to beat a human in the board game Go. Even though the game has simple rules, there are far too many possibilities for a computer to calculate the best next option deterministically. I wondered if such an approach could be useful in coping with certain aspects of biological complexity confronting us."
"The neural net was able to find patterns and interactions between the variables that would have been otherwise impossible to uncover," he concluded.