-
Advertorial
-
FOCUS
-
Guide
-
Lifestyle
-
Tech and Vogue
-
TechandScience
-
CHTF Special
-
Nanhan
-
Futian Today
-
Hit Bravo
-
Special Report
-
Junior Journalist Program
-
World Economy
-
Opinion
-
Diversions
-
Hotels
-
Movies
-
People
-
Person of the week
-
Weekend
-
Photo Highlights
-
Currency Focus
-
Kaleidoscope
-
Tech and Science
-
News Picks
-
Yes Teens
-
Fun
-
Budding Writers
-
Campus
-
Glamour
-
News
-
Digital Paper
-
Food drink
-
Majors_Forum
-
Speak Shenzhen
-
Business_Markets
-
Shopping
-
Travel
-
Restaurants
-
Hotels
-
Investment
-
Yearend Review
-
In depth
-
Leisure Highlights
-
Sports
-
World
-
QINGDAO TODAY
-
Entertainment
-
Business
-
Markets
-
Culture
-
China
-
Shenzhen
-
Important news
在线翻译:
szdaily -> Speak Shenzhen
AI attempts to write the next ‘Game of Thrones’ book
    2017-September-4  08:53    Shenzhen Daily

After feeding a type of AI known as a recurrent neural network the roughly 5,000 pages of Martin’s five previous books, software engineer Zack Thoutt has used the algorithm to predict what will happen next.

According to the AI’s predictions, some long-held fan theories do play out — in the five chapters generated by the algorithm so far, Jaime ends up killing Cersei, Jon rides a dragon, and Varys poisons Daenerys.

Each chapter starts with a character’s name, just like Martin’s actual books.

But in addition to backing up what many of us already suspect will happen, the AI also introduces some fairly unexpected plot turns that we’re pretty sure aren’t going to be mirrored in either the TV show or Martin’s books, so we wouldn’t get too excited just yet.

For example, in the algorithm’s first chapter, written from Tyrion’s perspective, Sansa turns out to be a Baratheon.

“It’s obviously not perfect,” Thoutt said. “It isn’t building a long-term story and the grammar isn’t perfect. But the network is able to learn the basics of the English language and structure of George R.R. Martin’s style on its own.”

Neural networks are a type of machine learning algorithm that are inspired by the human brain’s ability to not just memorize and follow instructions, but actually learn from past experiences.

In theory, Thoutt’s algorithm should be able to create a true sequel to Martin’s existing work, based off things that have already happened in the novels.

But in practice, the writing is clumsy and, most of the time, nonsensical. And it also references characters that have already died.

“A perfect model would take everything that has happened in the books into account and not write about characters being alive when they died two books ago,” Thoutt said.

“The reality, though, is that the model isn’t good enough to do that. It makes a lot of mistakes because the technology to train a perfect text generator that can remember complex plots over millions of words doesn’t exist yet.”

Words to Learn 相关词汇

【算法】suànfǎ algorithm a sequence of steps designed for programing a computer to solve a specific problem

【荒谬的】huāngmìu de nonsensical having little or no meaning, making little or no sense

软件工程师扎克·图特让一种名为循环神经网络的人工智能技术学习了《冰与火之歌》前五部近5000页的内容,然后利用该算法预测接下来的情节。

根据人工智能的预测,一些粉丝早前的推测的确出现了。在该算法目前撰写的五章内容中,詹姆最终杀死了瑟曦,囧雪成了龙骑士,而瓦里斯毒死了龙母。

和马丁本人撰写的小说一样,每章打头的文字都是一个角色的名字。

不过,我们也不要太过兴奋,因为除了存在很多人已经预测会发生的剧情外,这个人工智能算法还引入了一些令人意外的情节,绝对不会出现在电视剧或马丁的小说中。

例如,算法编写的第一章采用小恶魔的视角,这一章揭示珊莎其实属于拜拉席恩家族。

图特说,“这个算法显然不完美,它不能编写长篇故事,语法也有问题。但是神经网络可以自学英语的基本语言知识以及马丁的文风结构。”

神经网络是一种机器学习算法,设计灵感来自于人脑的记忆能力、遵循指令的能力以及从过去经验学习的能力。

理论上,图特的算法应该能基于书中已经出现的剧情创作出《冰与火之歌》真正的续集。

但实际上,这个算法的写作能力还很低级,大部分内容都不知所云,还会提到已经死掉的角色。

图特说:“完美的算法模型能把书中的所有剧情考虑在内,且不会让两部以前去世的角色再次出现。”

“然而,实际上这个算法现在还不完善。完美的文字创作机器可以记住数百万字的复杂剧情,现在的技术还不能训练出这种功能,它会犯很多错误。”

(Chinadaily.com.cn)

深圳报业集团版权所有, 未经授权禁止复制; Copyright 2010, All Rights Reserved.
Shenzhen Daily E-mail:szdaily@szszd.com.cn