tensorflow, subconscious and system 1

大致看了一下tensorflow的tutorial各种案例

感觉上tensorflow解决了一个mapping的问题

模式识别本身是一个mapping问题,就是从一堆的输入映射到一些的输出

比如给一张猫的图片,识别出里面是猫

而识别属于subconscious,据说一个人绝大部分决策出于subconscious,比如一个人开车

在think fast and slow这本书里,这对应于system 1

System 1 produces the fast, intuitive reactions and instantaneous decisions that govern most of our lives. System 2 is the deliberate type of thinking involved in focus, deliberation, reasoning or analysis – such as calculating a complex math problem, exercising self-control, or performing a demanding physical task.

tensorflow或者deep learning感觉上解决了system 1的问题

其实alphago同时结合了system 1和system 2。剪枝搜索属于system 2。形势判断和下一步选点属于system 1。其实system 1一直属于比较难的范畴,但是因为deep learning给突破了。

现在想想tensorflow或者deep learning真的有很多应用。所有subconscious的事情都可以用deep learning做。

比如人脸识别,语音识别,开车,踢球,投篮,唱歌,跳舞,甚至写程序中的某些部分

tensorflow之于高级编程语言就如同高级语言之如汇编语言

tensorflow基本上可以取代计算机博士了。几乎每个人都可弄出一个学习系统。只要找到足够的训练数据。而这并不难。

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s