PxPixel
Test tube artificial neural network recognises 'molecular handwriting' - TechSource International - Leaders in Technology News

Test tube artificial neural network recognises 'molecular handwriting'

Demonstrates the capacity to program AI into synthetic biomolecular circuits.
Author:
Publish date:
Conceptual illustration of a droplet containing an artificial neural network made of DNA that has been designed to recognise complex and noisy molecular information, represented as 'molecular handwriting.'

Conceptual illustration of a droplet containing an artificial neural network made of DNA that has been designed to recognise complex and noisy molecular information, represented as 'molecular handwriting.'

Researchers at Caltech have developed an artificial neural network made out of DNA that can solve a classic machine learning problem: correctly identifying handwritten numbers. The work is a significant step in demonstrating the capacity to program artificial intelligence into synthetic biomolecular circuits.

The work was done in the laboratory of Lulu Qian, assistant professor of bioengineering. A paper titled "Scaling up molecular pattern recognition with DNA-based winner-take-all neural networks," appeared in the journal Nature online on July 4.

"Though scientists have only just begun to explore creating artificial intelligence in molecular machines, its potential is already undeniable," said Qian. 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 Qian laboratory's ultimate goal for this work is to program intelligent behaviours (the ability to compute, make choices, and more) with artificial neural networks made out of DNA.

"Humans each have over 80 billion neurons in the brain, with which they make highly sophisticated decisions. Smaller animals such as roundworms can make simpler decisions using just a few hundred neurons. In this work, we have designed and created biochemical circuits that function like a small networkof neurons to classify molecular information substantially more complex than previously possible," says Qian.

To illustrate the capability of DNA-based neural networks, lead author of the study Kevin Cherry chose a task that is a classic challenge for electronic artificial neural networks: recognising handwriting.

Human handwriting can vary widely, and so when a person scrutinises a scribbled sequence of numbers, the brain performs complex computational tasks in order to identify them. Because it can be difficult even for humans to recognise others' sloppy handwriting, identifying handwritten numbers is a common test for programming intelligence into artificial neural networks. These networks must be "taught" how to recognise numbers, account for variations in handwriting, then compare an unknown number to their so-called memories and decide the number's identity.

In the work Cherry, who is the first author on the paper, demonstrated that a neural network made out of carefully designed DNA sequences could carry out prescribed chemical reactions to accurately identify "molecular handwriting." Unlike visual handwriting that varies in geometrical shape, each example of molecular handwriting does not actually take the shape of a number. Instead, each molecular number is made up of 20 unique DNA strands chosen from 100 molecules, each assigned to represent an individual pixel in any 10 by 10 pattern. These DNA strands are mixed together in a test tube.

The DNA neural network can classify it into up to nine categories, each representing one of the nine possible handwritten digits from 1 to 9.

Qian and Cherry plan to develop artificial neural networks that can learn, forming "memories" from examples added to the test tube. This way, Qian says, the same smart soup can be trained to perform different tasks.