Artificial intelligence network made of DNA can identify 'molecular handwriting' - The Financial Express

Scientists have developed a neural network using DNA, which can correctly identify numbers encoded in molecules using machine learning, an advance that may pave the way for biological machines with artificial intelligence. Artificial neural networks are mathematical models inspired by the human brain. Despite being much simplified compared to their biological counterparts, artificial neural networks function like networks of neurons and are capable of processing complex information. The ultimate goal for this work is to programme intelligent behaviours (the ability to compute, make choices, and more) with artificial neural networks made out of DNA. "In this work, we have designed and created biochemical circuits that function like a small network of neurons to classify molecular information substantially more complex than previously possible," said Lulu Qian, assistant professor at California Institute of Technology in the US.