DeepMind已開發具有三維想象力的視覺計算機

DeepMind, Google's artificial intelligence subsidiary in London, has developed a self-training vision computer that generates "a full 3D model of a scene from just a handful of 2D snapshots", according to its chief executive.

位於倫敦的谷歌人工智能子公司DeepMind，近日開發了一款自我訓練的視覺計算機。據其首席執行官介紹，這款計算機“僅利用幾張2D快照就能生成一個完整的3D場景模型”。

The system, called the Generative Query Network, can then imagine and render the scene from any angle, said Demis Hassabis.

傑米斯·哈薩比斯表示，這套被稱爲“生成式查詢網絡”的系統可以從任何角度想象和呈現場景。

GQN is a general-purpose system with a vast range of potential applications, from robotic vision to virtual reality simulation.

GQN是一個通用系統，具有從機器人視覺到虛擬現實模擬的廣泛的應用潛力。

"Remarkably, the DeepMind scientists developed a system that relies only on inputs from its own image sensors -- and that learns autonomously and without human supervision," said Matthias Zwicker, a computer scientist at the University of Maryland.

馬里蘭大學的計算機科學家馬蒂亞斯·茨威格稱：“值得一提的是，DeepMind的科學家開發了只依賴自身圖像傳感器所輸入信息，就可以自主學習的系統，且無需人類監督。”

This is the latest in a series of high-profile DeepMind projects, which are demonstrating a previously unanticipated ability by AI systems to learn by themselves, once their human programmers have set the basic parameters.

這是DeepMind一系列備受矚目的項目中最新的一個，這些項目展示了一種之前未曾預料到的人工智能系統自學能力--在編程人員爲其設定基本參數之後。

In October DeepMind's AlphaGo taught itself to play Go, the ultra-complex board game, far better than any human player. Last month another DeepMind AI system learned to find its way around a maze, in a way that resembled navigation by the human brain.

去年10月，DeepMind的AlphaGo自學了圍棋這種超級複雜的棋類遊戲，然後輕鬆擊敗了人類棋手。上個月，DeepMind的另一個人工智能系統學會了在迷宮中尋找路徑，其方式類似於人類大腦的導航功能。

Future GQN systems promise to be more versatile and to require less processing power than today's computer vision techniques, which are trained with large data sets of annotated images produced by humans.

未來的GQN系統有望比今天的計算機視覺技術的功能更爲強大，所需的處理能力也會更低。目前的計算機視覺技術是用由人類生成的大量帶標註的圖像數據集來訓練的。