Visualizing Our Dreams with AI

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.

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

此前，研究人員已創建出能夠將文本轉換為圖像的AI模型。AI可以學習來自測試和圖像中的大量數據，從而實現轉換。據《科學》雜志報道，日本大阪大學的研究團隊訓練了一個名為“穩定擴散”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明尼蘇達大學提供的在線數據集，其中包括4名參與者觀看10 000張照片時的腦部掃描結果，該掃描結果由功能性核磁共振成像（fMRI）記錄。

隨后，AI通過分析fMRI數據顯示的血流變化了解大腦活動——大腦的某部分被激活時，會有更多的血液流向該區域，然后將大腦活動與看到的照片相匹配。通過這種方法，AI了解到觀看不同照片時人類大腦的反應。

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，在同一批參與者觀看玩具熊、飛機、時鐘和火車的照片時，研究人員用AI分析了額外的腦部掃描結果。例如，一個人看著一架飛機時，AI會使用大腦掃描數據生成一個非常模糊的飛機圖像。然后，AI會啟動之前的“文本轉圖像”模式，并給自己輸入“飛機”這一關鍵詞，以提高圖像的質量。據研究人員稱，最終得到的圖像“幾可亂真”，且準確率高達約80%。

美國普林斯頓大學的科學家Ariel Goldstein在接受《科學》雜志采訪時表示，這項新研究創造了一種結合文本和圖像來“破譯大腦”的新方法。未來，科研人員們希望這項技術可以用來記錄幻想和夢境，或是讓人們了解其他動物對現實的感知有何不同。

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；意識到；察覺到