A new type of computer can use the behaviour of magnetic particles to recognise handwritten digits. If made smaller and faster it should be able to process information in an energy-efficient way.

By using the MNIST dataset, a well-known collection of handwritten numbers, the calculator could identify digits in just 18 seconds. If you want to learn how, check out his full video on it here.

He tested 36 handwritten numbers and the test tube neural network correctly identified all of them. His system theoretically has the capability of classifying over 12,000 handwritten 6s and 7s ...

Helpfully, these documents include a number of handwritten numbers. Baqué then personally transported two of the boards, and the handwriting samples, to California for examination by PSA.

By using the MNIST dataset, a well-known collection of handwritten numbers, the calculator could identify digits in just 18 seconds. If you want to learn how, check out his full video on it here.

In other tests, the system was even able to recognize handwritten numbers with an accuracy of 72 percent. It was also very stable, with no change in the response to light after 129 weeks.

Given a particular example of molecular handwriting, 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.

The proof-of-principle glass AI that Yu’s team created can distinguish between handwritten single digit numbers. It can also recognise, in real time, when a number it is presented with changes ...