After waking up， you may feel frustrated that you cannot recall the dreams you had last night. Artificial intelligence (AI) may be able to help.

Previously， there have been AI models that can turn text into images. They can do this by learning from a large amount of data from both tests and images. Researchers from Osaka University in Japan have trained an AI system called Stable Diffusion to re-create images based on people’s brain scans， reported Science magazine.

The researchers used an online data set provided by the University of Minnesota， US， which consisted of brain scans from four participants as they each viewed a set of 10，000 photos. The scans were recorded by functional magnetic resonance imaging (fMRI).

The AI then learned about the brain activities by analyzing changes in blood flow shown by the fMRI data—when a part of the brain is activated， more blood will flow to it. It then matched the brain activities with the photos. Through this method， AI learned how human brains would react when seeing different photos.

如果醒來(lái)后記不得前一晚做的夢(mèng)，你可能會(huì)覺(jué)得沮喪，而人工智能（AI）或許可以幫上忙。

此前，研究人員已創(chuàng)建出能夠?qū)⑽谋巨D(zhuǎn)換為圖像的AI模型。AI可以學(xué)習(xí)來(lái)自測(cè)試和圖像中的大量數(shù)據(jù)，從而實(shí)現(xiàn)轉(zhuǎn)換。據(jù)《科學(xué)》雜志報(bào)道，日本大阪大學(xué)的研究團(tuán)隊(duì)訓(xùn)練了一個(gè)名為“穩(wěn)定擴(kuò)散”的AI模型，可以基于人們的大腦掃描再生成圖像。

研究人員使用了美國(guó)明尼蘇達(dá)大學(xué)提供的在線(xiàn)數(shù)據(jù)集，其中包括4名參與者觀(guān)看10 000張照片時(shí)的腦部掃描結(jié)果，該掃描結(jié)果由功能性核磁共振成像（fMRI）記錄。

隨后，AI通過(guò)分析fMRI數(shù)據(jù)顯示的血流變化了解大腦活動(dòng)——大腦的某部分被激活時(shí)，會(huì)有更多的血液流向該區(qū)域，然后將大腦活動(dòng)與看到的照片相匹配。通過(guò)這種方法，AI了解到觀(guān)看不同照片時(shí)人類(lèi)大腦的反應(yīng)。

Finally， the researchers tested the AI on additional brain scans from the same participants when they viewed photos of a toy bear， airplane， clock and train. If the person looked at an airplane， for example， the AI would use the brain scan data to create an image of a very blurry airplane. Then， it would turn on the previous “text-to-image” model and improve the quality of the image by feeding itself the keyword “airplane”. The final images were “convincing” with about 80 percent of accuracy， according to the researchers.

The new study created a novel approach that combines texts and images to “decipher the brain”， Ariel Goldstein from Princeton University， US， told Science magazine. In the future， scientists hope that the technology can be used to record imagined thoughts and dreams or allow people to understand how differently other animals perceive reality.

最后，在同一批參與者觀(guān)看玩具熊、飛機(jī)、時(shí)鐘和火車(chē)的照片時(shí)，研究人員用AI分析了額外的腦部掃描結(jié)果。例如，一個(gè)人看著一架飛機(jī)時(shí)，AI會(huì)使用大腦掃描數(shù)據(jù)生成一個(gè)非常模糊的飛機(jī)圖像。然后，AI會(huì)啟動(dòng)之前的“文本轉(zhuǎn)圖像”模式，并給自己輸入“飛機(jī)”這一關(guān)鍵詞，以提高圖像的質(zhì)量。據(jù)研究人員稱(chēng)，最終得到的圖像“幾可亂真”，且準(zhǔn)確率高達(dá)約80%。

美國(guó)普林斯頓大學(xué)的科學(xué)家Ariel Goldstein在接受《科學(xué)》雜志采訪(fǎng)時(shí)表示，這項(xiàng)新研究創(chuàng)造了一種結(jié)合文本和圖像來(lái)“破譯大腦”的新方法。未來(lái)，科研人員們希望這項(xiàng)技術(shù)可以用來(lái)記錄幻想和夢(mèng)境，或是讓人們了解其他動(dòng)物對(duì)現(xiàn)實(shí)的感知有何不同。

Word Bank

activate /'?kt?ve?t/ v. 激活；使活化

How to activate the database is a problem.

novel /'n?vl/ adj. 新穎的；與眾不同的

perceive /p?'si?v/ v. 注意到；意識(shí)到；察覺(jué)到