TED演講者：Sofia Crespo / 索菲亞·克雷斯波

演講標題：AI-generated creatures that stretch the boundaries of imagination / AI 生成的生物幫助我們拓寬想象的邊界

內(nèi)容概要：Can AI help us see beyond our human capabilities? Through a kaleidoscopic blend of technology, nature and art, neural artist Sofia Crespo brings to life animals that push the boundaries of creativity and imagination. Her artistic renditions of chimeras combine images of real-world endangered species to create something totally new -- with the intention of inspiring real-world conservation. Witness a speculative study of creatures that never existed, brought to life by AI.

AI 可以幫我們超越人類的能力嗎？神經(jīng)網(wǎng)絡藝術家索菲亞·克雷斯波（Sofia Crespo）向我們展示了融合科技、自然和藝術的薈萃，為我們帶來了拓寬我們創(chuàng)意和想象邊界的動物們。她對合成生物的藝術呈現(xiàn)融合了真實世界中瀕危物種的照片，創(chuàng)造了嶄新的物種，同時懷著鼓勵真實世界中的生物保護的目的。一起來見證這關于不存在的生物的推測性研究，由 AI 實現(xiàn)。

*******************************************

【1】I'd like to start by asking you to imagine a color that you've never seen before.

我想先請你們想象一種 從未見過的顏色。

【2】Just for a second give this a try.

姑且來試一下吧。

【3】Can you actually visualize a color that you've never been able to perceive?

你能想象出一種無法感知的顏色嗎？

【4】I never seem to get tired of trying this although I know it's not an easy challenge.

我對此樂此不疲, 即使我知道這并不容易。

【5】And the thing is, we can't imagine something without drawing upon our experiences.

問題是, 如果不基于我們自身的經(jīng)歷, 我們就無法想象出某些東西。

【6】A color we haven't yet seen outside the spectrum we can perceive is outside our ability to conjure up.

我們從未見過的顏色, 超出了我們可以感知的光譜, 也就超出了我們的想象力。

【7】It's almost like there's a boundary to our imagination where all the colors we can imagine can only be various shades of other colors we have previously seen.

這就感覺像是 我們的想象力有一個邊界, 我們可以想象出的所有顏色 只能是我們之前見過的 顏色的不同變體。

【8】Yet we know for a fact that those color frequencies outside our visible spectrum are there.

但是我們知道有這么一個事實, 超出可見光頻譜的 顏色頻率確實存在。

【9】And scientists believe that there are species that have many more photo receptors than just the three color ones we humans have.

科學家們相信有些物種 擁有更多的光感受器, 比我們?nèi)祟悡碛械?三色光感受器要多。

【10】Which, by the way, not all humans see the world in the same way.

順帶一提, 不是所有人眼中的世界 都是一樣的。

【11】Some of us are colorblind to various degrees, and very often we don't even agree on small things, like if a dress on the internet is blue and black or white and gold.

有些人會有不同程度的色盲, 我們經(jīng)常會 就一些小事爭論不休, 比如網(wǎng)上的一條裙子是 藍黑還是白金。

【12】But my favorite creature, one of my favorite creatures, is the peacock mantis shrimp, which is estimated to have 12 to 16 photo receptors.

但是我最喜歡的生物, 最喜歡的生物之一, 是雀尾螳螂蝦, 估計有 12 至 16 個光感受器。

【13】And that indicates the world to them might look so much more colorful.

意味著它們眼中的世界 會更加色彩斑斕。

【14】So what about artificial intelligence?

人工智能（AI）呢？

【15】Can AI help us see beyond our human capabilities?

AI 可以幫助我們 超越人類的視覺嗎？

【16】Well, I've been working with AI for the past five years, and in my experience, it can see within the data it gets fed.

我在過去的五年里 一直在用 AI 工作, 根據(jù)我的經(jīng)驗,它能看到的內(nèi)容 取決于輸入的數(shù)據(jù)。

【17】But then you might be wondering, OK, if AI can't help imagine anything new, why would an artist see any point in using it?

但是你可能會想,好吧, 如果 AI 不能想象出新東西, 藝術家為什么要用它呢？

【18】And my answer to that is because I think that it can help augment our creativity as there's value in creating combinations of known elements to form new ones.

我的答案是,我認為 AI 可以增強我們的創(chuàng)造力, 通過組合既有的元素,創(chuàng)造新元素, 它就產(chǎn)生了價值。

【19】And this boundary of what we can imagine based on what we have experienced is the place that I have been exploring.

基于我們的經(jīng)歷形成的 想象力的邊界 是我探索的領域。

【20】For me, it started with jellyfish on a screen at an aquarium and wearing those old 3D glasses, which I hope you remember, the ones with the blue and red lens.

對我來說,一切始于 水族館屏幕上的水母, 我戴著那種老式 3D 眼鏡, 但愿你還有印象, 鏡片一片藍一片紅的那種。

【21】And this experience made me want to recreate their textures.

這個體驗讓我想重現(xiàn)它們的質感。

【22】But not just that, I also wanted to create new jellyfish that I hadn't seen before, like these.

但是不僅如此, 我還想創(chuàng)造我從未見過的 新型水母,就像這種。

【23】And what started with jellyfish, very quickly escalated to other sea creatures like sea anemone, coral and fish.

我從水母開始, 迅速擴展到了其他海洋生物, 比如?？⑸汉骱汪~類。

【24】And then from there came amphibians, birds and insects.

然后是兩棲動物、鳥類和昆蟲。

【25】And this became a series called “Neural Zoo”.

它們組成了一個系列,名為 《神經(jīng)動物園》（Neural Zoo）。

【26】But when you look closely, what do you see?

但是如果你仔細看看, 你會看見什么呢？

【27】There's no single creature in these images.

這些圖片里的都不是單一生物。

【28】And AI augments my creative process by allowing me to distill and recombine textures.

AI 增強了我發(fā)揮創(chuàng)意的過程, 讓我可以提取、 重組它們的質感。

【29】And that's something that would otherwise take me months to draw by hand.

如果我要手繪, 可能要花上好幾個月。

【30】Plus I'm actually terrible at drawing.

而且我畫畫水平太差了。

【31】So you could say, in a way, what I'm doing is a contemporary version of something that humans have already been doing for a long time, even before cameras existed.

你可以這么說, 從某種角度來看,我在做的 是早在相機出現(xiàn)之前, 人類就一直在做的事, 但是是它的現(xiàn)代版本。

【32】In medieval times, people went on expeditions, and when they came back they would share about what they saw to an illustrator.

中世紀, 人們踏上遠征, 回來之后他們會向畫師 描述他們的見聞。

【33】And the illustrator, having never seen what was being described, would end up drawing based on the creatures that they had previously seen and in the process creating hybrid animals of some sort.

畫師從未見過描繪之物, 于是他們會按照 他們之前見過的生物繪制, 再自創(chuàng)一些合成動物。

【34】So an explorer might describe a beaver, but having never seen one, the illustrator might give it the head of a rodent, the body of a dog and a fish-like tail.

也許出行者描述了一只海貍, 但是畫師從沒見過海貍, 于是畫了嚙齒動物的頭部, 狗的身子和類似魚類的尾巴。

【35】In the series “Artificial Natural History”, I took thousands of illustrations from a natural history archives, and I fed them to a neural network to generate new versions of them.

我在《人工自然歷史》 （Artificial Natural History）系列中 從自然歷史檔案中 提取了幾千張插圖, 輸入神經(jīng)網(wǎng)絡, 產(chǎn)生新版本的插圖。

【36】But up until now, all my work was done in 2D.

但是時至今日,我的所有作品 都是以 2D 的形式完成的。

【37】And with the help of my studio partner, Feileacan McCormick, we decided to train a neural network on a data set of 3D scanned beetles.

在我的工作室伙伴菲力肯·麥考密克 （Feileacan McCormick）的幫助下, 我們打算基于經(jīng) 3D 掃描的 甲蟲的數(shù)據(jù)集訓練一個神經(jīng)網(wǎng)絡。

【38】But I must warn you that our first results were extremely blurry, and they looked like the blobs you see here.

但是我要提醒你的是 我們的第一批結果非常模糊, 如圖所示的一坨。

【39】And this could be due to many reasons, but one of them being that there aren't really a lot of openly available data sets of 3D insects.

導致這種情況的原因可能有很多, 但是其中一個原因是公開可用的 3D 昆蟲數(shù)據(jù)集比較有限。

【40】And also we were repurposing a neural network that normally gets used to generate images to generate 3D.

而且我們也改變了神經(jīng)網(wǎng)絡的功能, 由常見的生成圖片 轉向了生成 3D 結果。

【41】So believe it or not, these are very exciting blobs to us.

無論如何,它們都是 令我們激動的一坨物體。

【42】But with time and some very hacky solutions like data augmentation, where we threw in ants and other beetle-like insects to enhance the data set, we ended up getting this, which we've been told they look like grilled chicken.

隨著時間的推移和 一些另辟蹊徑的產(chǎn)品的出現(xiàn), 如數(shù)據(jù)增強, 如果我們輸入螞蟻 或者其他類似甲蟲的昆蟲 增強了數(shù)據(jù)集, 我們會得到這樣的結果, 有人說它們長得像烤雞。

【43】(Laughter) But hungry for more, we pushed our technique, and eventually they ended up looking like this.

（笑聲） 但是我們的野心不止于此, 我們改進了技術, 最終得到了這樣的結果。

【44】We use something called 3D style transfer to map textures onto them, and we also trained a natural language model to generate scientific-like names and anatomical descriptions.

我們用了一項叫做 “3D 風格遷移”的技術 我們還訓練了一個自然語言模型, 生成科研風的名字和 生物結構描述。

【45】And eventually we even found a network architecture that could handle 3D meshes.

我們最后甚至找到了一個 網(wǎng)絡體系結構處理 3D 網(wǎng)格。

【46】So they ended up looking like this.

最后的結果是這樣的。

【47】And for us, this became a way of creating kind of a speculative study --

對我們來說,這已經(jīng)類似于 一種推測性研究……

【48】(Applause) A speculative study of creatures that never existed, kind of like a speculative biology.

（掌聲） 關于不存在的生物的 推測性研究, 類似猜想生物。

【49】But I didn't want to talk about AI and its potential unless it brought me closer to a real species.

但是我并不想談論 AI 和它的潛力, 除非 AI 產(chǎn)生的結果 接近真實存在的物種。

【50】Which of these do you think is easier to find data about online?

圖上的兩種生物,你覺得哪個 更容易在網(wǎng)上找到數(shù)據(jù)？

【51】(Laughter) Yeah, well, as you guessed correctly, the red panda.

（笑聲） 你猜的沒錯,小熊貓。

【52】And this maybe could be due to many reasons, but one of them being how cute they are, which means we photograph and talk about them a lot, unlike the boreal felt lichen.

可能會有很多原因, 但是其中一個原因就是 它們太可愛了, 所以我們總是會給它們拍照, 討論它們, 北方氈狀地衣就沒這種待遇了。

【53】But both of them are classified as endangered.

但是這兩種生物 都被定為了頻危物種,

【54】So I wanted to bring visibility to other endangered species that don't get the same amount of digital representation as a cute, fluffy red panda.

我想請大家都去關注一下 其他的瀕危物種, 它們不一定會像 毛茸茸的可愛小熊貓那樣 擁有那么高的數(shù)字化曝光度。

【55】And to do this, we trained an AI on millions of images of the natural world, and then we prompted with text to generate some of these creatures.

為了達成這個目標, 我們用自然界的百萬張圖片 訓練了 AI, 然后我們用文字提示, 生成一些生物。

【56】So when prompted with a text, "an image of a critically endangered spider, the peacock tarantula"

如果我們輸入這樣的提示: “藍寶石華麗雨林—— 一種極度瀕危的蜘蛛的圖片”

【57】and its scientific name, our model generated this.

和它的學名, 我們的模型會輸出這樣的結果。

【58】And here's an image of the real peacock tarantula, which is a wonderful spider endemic to India.

這是一張真實的 藍寶石華麗雨林的照片, 它是一種分布于 印度本土的華麗蜘蛛。

【59】But when prompted with a text "an image of a critically endangered bird, the mangrove finch,"

如果我們輸入這樣的提示: “紅樹林雀—— 一種極度瀕危的鳥類的圖片”,

【60】our model generated this.

我們的模型會生成這樣的結果。

【61】And here's a photo of the real mangrove finch.

這是真實的紅樹林雀的照片。

【62】Both these creatures exist in the wild, but the accuracy of each generated image is fully dependent on the data available.

這兩種動物都在自然界中真實存在, 但是生成圖片的準確度 完全取決于可用的數(shù)據(jù)。

【63】These chimeras of our everyday data to me are a different way of how the future could be.

由我們?nèi)粘?shù)據(jù)產(chǎn)生的“怪物” 對我來說是對未來的另一種暢想。

【64】Not in a literal sense, perhaps, but in the sense that through practicing the expanding of our own imagination about the ecosystems we are a part of, we might just be better equipped to recognize new opportunities and potential.

也許不是字面意思, 但是通過擴展我們對 我們所處生態(tài)環(huán)境的想象, 我們也許更有可能 會發(fā)現(xiàn)新機會和新潛力。

【65】Knowing that there's a boundary to our imagination doesn't have to feel limiting.

清楚地知道 我們的想象力是有界限的, 并不代表我們得束手束腳。

【66】On the contrary, it can help motivate us to expand that boundary further and to seek out colors and things we haven't yet seen and perhaps enrich our imagination as a result.

相反, 這可以鼓勵我們拓展邊界, 尋找我們沒有見過的顏色和事物, 也許最終會豐富我們的想象。

【67】So thank you.

謝謝。

【68】(Applause)