Tech News

Scientists made an AI that reads your mind so it can generate portraits you’ll find attractive

A team of researchers recently developed a mind-reading AI that uses an individual’s personal preferences to generate portraits of attractive people who don’t exist.

Computer-generated beauty truly is in the AI of the beholder.

The big idea: Scientists from the University of Helsinki and the University of Copenhagen today published a paper detailing a system by which a brain-computer-interface is used to transmit data to an AI system which then interprets that data and uses it to train an image generator.

According to a press release from the University of Helsinki:

Initially, the researchers gave a generative adversarial neural network (GAN) the task of creating hundreds of artificial portraits. The images were shown, one at a time, to 30 volunteers who were asked to pay attention to faces they found attractive while their brain responses were recorded via electroencephalography (EEG) …

The researchers analysed the EEG data with machine learning techniques, connecting individual EEG data through a brain-computer-interface (BCI) to a generative neural network.

Once the user’s preferences were interpreted, the machine then generated a new series of images, tweaked to be more attractive to the individual whose data it was trained on. Upon review, the researchers found that 80% of the personalized images generated by the machines stood up to the attractiveness test.

Background: Sentiment analysis is a big deal in AI, but this is a bit different. Typically, machine learning systems designed to observe human sentiment use cameras and rely on facial recognition. That makes them unreliable for use with the general public, at best.

But this system relies on a direct link up to our brainwaves. And that means it should be a fairly reliable indicator of positive or negative sentiment. In other words: the base idea seems sound enough in that you look at a picture you find pleasing and then an AI tries to make more pictures that trigger the same brain response.

Quick take: You could attempt to hypothetically extrapolate the potential uses for such an AI all day long and never decide whether it was ethical or not. On the one hand, there’s a treasure trove of psychological insight to be gleaned from a machine that can abstract what we like about a given image without relying on us to consciously understand it.

But, on the other hand, based on what bad actors can do with just a tiny sprinkling of data, it’s absolutely horrifying to think of what a company such as Facebook (that’s currently developing its own BCIs) or a political influence machine like Cambridge Analytica could do with an AI system that knows how to skip someone’s conscious mind and appeal directly to the part of their brain that likes stuff. 

You can read the whole paper here.

Published March 5, 2021 — 21:11 UTC

Repost: Original Source and Author Link

Tech News

Nosy AI reads a 300-year-old sealed letter — without opening it

Scientists have used an algorithm to read an unopened letter written 300 years ago — without breaking its seal.

The note had been securely shut through an archaic process known as “letterlocking.” The method was used to secure written communications for centuries before the widespread adoption of envelopes in the 1830s.

The intricate system of folds, tucks, and slits effectively turns the paper into its own envelope. Often, the notes were then sealed and rigged with anti-tamper devices.

The method was used by both everyday people and historical figures from Queen Elizabeth I of England to Marie Antoinette.

While the concealed letters contain valuable insights into the past, the packets themselves are also valuable historical artifacts.

[Read: How do you build a pet-friendly gadget? We asked experts and animal owners]

The researchers developed a computational method that can uncover their contents while also preserving the materials.

“Our work seeks to make an intervention in the conservation of cultural heritage,” they wrote in their study paper. “Once a document such as an unopened letter is damaged in the opening process, we lose a sense of the object as untouched and intact.”

Picking the letter locks

The team first scanned the folded documents with X-ray imagining equipment that was designed for use in dentistry.

Computational flattening algorithms were then applied to the scans. This generated 2D and 3D reconstructions of the letters in both folded and flat states. It also produced images of the writing surfaces and crease patterns in the documents.

The technique exposed the entire contents of a letter dated July 31, 1697.

It was sent by a legal professional called Jacques Sennacques to his cousin Pierre Le Pers, a French merchant living in The Hague.

The letter bears the mark “10” in red crayon on the address panel, indicating how much the recipient would have needed to pay for it. The address and price suggest the document was sent from Lille.

Inside the unfolded letterpack, Sennacques asks his cousin — with some urgency — for the death certificate of another relative:

I am writing to you a second time in order to remind you of the pains that I took on your behalf. It is important to me to have this extract you will do me  great pleasure to procure it for me to send me at the same time news of your health of all the family. I also pray that God maintains you in His Sainted graces & covers you with the blessings necessary to your salvation. Nothing more for the time being, except that I pray you to believe that I am completely, sir and cousin, your most humble & very obedient servant.

The missive was taken from a European postmaster’s trunk of 300-year-old undelivered post, known as the Brienne Collection

“We could simply have cut these letters open, but instead we took the time to study them for their hidden, secret, and inaccessible qualities,” said Daniel Starza Smith, lecturer in early modern English literature at King’s College London “We’ve learned that letters can be a lot more revealing when they are left unopened.”

The researchers say their technique could also virtually open a range of other historical texts, such as scrolls and books.

Sennacques’ letter alone own may not expose radical insights about the 17th century. But analyzed alongside other documents, it could broaden our understanding of the culture, politics, and people of early modern Europe.

You can read the study paper and view the unfolded letter in the journal Nature Communications.

Published March 3, 2021 — 15:33 UTC

Repost: Original Source and Author Link