您现在的位置是:Recording dreams? AI could help us do that using brain scan data >>正文
Recording dreams? AI could help us do that using brain scan data
上海品茶网 - 夜上海最新论坛社区 - 上海千花论坛16912人已围观
简介By subscribing, you agree to our Terms of Use and Policies You may unsubscribe at any time.Researche...
By subscribing, you agree to our Terms of Use and Policies You may unsubscribe at any time.
Researchers at Osaka University in Japan have successfully created an artificial intelligence (AI) model that can recreate images that people are seeing using their brain scans alone. Further work on this area could one day perhaps help us record dreams and allow paralyzed patients to communicate non-verbally.
The development of this technology is in line with advancements made in generative AI where algorithms can produce images based on text prompts provided by the user. In fact, the researchers used one such algorithm called Stable Diffusion which was released last year, alongside more popular services like OpenAI's DALL-E 2. The researchers also found that using the existing tool was a much more efficient method than previous research approaches that used energy-intensive AI models.
See AlsoTeaching AI to recreate images using brain scans
Since the algorithm is capable of generating images based on prompts, the researchers focused their attention on making the AI work with brain signals. To do so, they gathered information from different parts of the brain, such as the occipital lobes and temporal lobes that are involved in image perception.
The researchers used data from functional magnetic resonance imaging (fMRI) scans which are sensitive enough to detect differences in blood flow to active regions of the brain. The dataset used for training the AI contained fMRI data of four individuals as they each viewed a set of 10,000 photos.
Brain activity from the occipital lobe provided information to recreate the layout and perspective of the images while that from the temporal lobe provided data about people, objects, or scenery in the image. The researchers then used the data set to form links between text descriptions of the images and fMRI data.
The models were then used to test a portion of the brain scans from the four participants that were not used in training earlier. The researchers found that the AI algorithm could reconstruct around 1,000 images from these brain scans with 80 percent accuracy. This is the same efficiency that other researchers have previously achieved using more intensive approaches.
The models were custom trained for the four participants of the study, making this approach impractical when it comes to scaling it for a large number of users. The researchers are now working on refinements to the methods to make them easier to be adopted by a larger group of users.
When widely available, the technology could be used to record the thoughts and dreams of people and even allow them to create art by simply imagining it. The possibilities are endless.
Tags:
转载:欢迎各位朋友分享到网络,但转载请说明文章出处“上海品茶网 - 夜上海最新论坛社区 - 上海千花论坛”。http://www.jz08.com.cn/news/64122.html
相关文章
Cardano vs Solana: Here’s Why SOL is a Better Buy than ADA
Recording dreams? AI could help us do that using brain scan dataCardano and Solana price have been in a strong bearish trend in the past few months. SOL is trading...
阅读更多
Anchor Protocol (ANC) Price Soars as Terra’s LUNC and USTC Rebound
Recording dreams? AI could help us do that using brain scan dataAnchor Protocol price went parabolic on Thursday as investors cheered the strong performance of cryp...
阅读更多
Equilibrium integrates Polygon for cross
Recording dreams? AI could help us do that using brain scan dataEquilibrium has announced Polygon integration as it aims to offer cross-chain DeFi solutions to both...
阅读更多
热门文章
- Inveo's new cave protects bats from extreme temperatures
- Midjourney V5 rolls out with new features promising accessibility
- This new bifacial solar cell tech can deliver 3X power!
- New breakthrough could vastly improve forecasts for potentially disastrous solar storms
- IBM's Quantum System Two will help it unlock the 'full power of quantum computing'
- Princeton researchers help a bot tidy up using large language model
最新文章
OpenAI CEO warns Senate about AI interfering with elections
Binance’s CEO says the exchange is not a Chinese company
Binance’s CEO says the exchange is not a Chinese company
Elrond's EGLD token now available on Revolut
Celsius gets approval for a new Bitcoin mining plant
AngelBlock, DeFi protocol for crypto