许多人写了深度学习将如何掌控世界的文章,以及为什么要重视深度学习;我无法一一回应他们。 使用深度学习是最让我觉得变成了一个魔术师的事。最近我清楚地看到,每一个伟大的软件将在未来3年内由深度学习驱动发展。 然而,当下深度学习仍不是最主流,所以我想分享一些非常有才华的贡献者的工作,希望能够使深度学习离大家更接近一点。
Here’s ten reasons why I think deep learning is living up to the hype…
…it’s equally impressive for anime art
2 模仿人类语音阅读 Deep learning has enabled a text-to-speech system that is almostindistinguishable from human voice. Think of the possibilities!
https://deepmind.com/blog/wavenet-generative-model-raw-audio/
https://soundcloud.com/oliver-cameron-330659812/wavenet-sample-2
3 创作经典音乐 Deep learning can compose classical music that you’d believe to be created by a human
https://soundcloud.com/oliver-cameron-330659812/wavenet-sample-1
4 模仿画家的画风作画 Deep learning can replicate the style of your favorite painter with the image of your choice
这种DL技术的作画论文在这里.
5 使用深度学习创作字体 Deep learning can even generate fonts!
6 深度学习修补图片缺失部分 Deep learning can auto-fill missing parts of an image, by predicting what should be in that space
7 让机器人训练成直立行走 Deep learning can train a robot to walk like a human
或者像人一样拿东西…or train a robot to grasp objects like a human
8 为图片自动取一个标题 Deep learning can caption an image, just like a human would
9 想要画一幅漂亮的风景画? Want to sketch a beautiful landscape but can’t draw? Don’t worry, deep learning can take it from here!
10 让深度学习来开车! Best of all (at least to me), you can train a deep neural network to steer a car**, just like a human
为什么我确信深度学习是革命性的? 如果你仔细看看机器正在执行的上述任务,你会看到一个共同的特性:创造力。 机器,虽然通过人类给予的数据进行训练,能够展示接近真实艺术的性格。
我们花了几十年的时间建设和优化机器,让其计算能力更为强大。 在接下来的十年中,我希望我们能够发现,当我们的软件创造性地思考时,人类将能够被赋予什么能力。
Ref
https://medium.com/@olivercameron/deep-learning-is-revolutionary-d0f3667bafa0#.av4uxfuwj