at Osaka University in Japan have developed a much simpler approach using Stable Diffusion, a text-to-image generator released by Stability AI in August 2022. Their new method involves thousands, rather than millions, of parameters.When used normally, Stable Diffusion turns a text prompt into an image by starting with random visual noise and tweaking it to produce images that resemble ones in its training data that have similar text captions.
Using around 90 per cent of the brain-imaging data, the pair trained a model to make links between fMRI data from a brain region that processes visual signals, called the early visual cortex, and the images that people were viewing.Sign up to newsletter After training, these two models – which had to be customised to each individual – could translate brain-imaging data into forms that were directly fed into the Stable Diffusion model. It could then reconstruct around 1000 of the images people viewed with about 80 per cent accuracy, without having been trained on the original images.
This isn’t a good thing.
Čtení myšlenek se stává realitou...
the rational revolution is coming, and I don't even have to say anything!
Mind reading! I wonder if police investigating a crime could flash images of people and places up - and the computer could know if they have seen them before and how often. What would this mean for privacy?
This is scary. Just heard yesterday that AI can now imitate your voice. Imagine the repercussions of that! This world is becoming more dangerous every day for ordinary people and more lucrative for people looking to do harm.
Why?
These techniques typically involve measuring the activity in different parts of the brain using functional magnetic resonance imaging (fMRI) or electroencephalography (EEG) and then using machine learning algorithms to map the brain activity to corresponding images.
impressive
big deal...my brain analyses what I see using optical nerves and rods and cones and such...
Technology Technology Latest News, Technology Technology Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
Source: SciTechDaily1 - 🏆 84. / 68 Read more »
Source: petapixel - 🏆 527. / 51 Read more »