ADM-201 dump PMP dumps pdf SSCP exam materials CBAP exam sample questions

《机器学习Python实践》#1 课程介绍 – 译学馆
未登录,请登录后再发表信息
最新评论 (0)
播放视频

《机器学习Python实践》#1 课程介绍

Practical Machine Learning Tutorial with Python Intro p.1

好的 女士先生们 欢迎来到
Well, girls and guys and welcome to an
深度机器学习系列教程中
in-depth machine learning tutorial series.
本系列教程的的目的是为了给你
The objective of this tutorial series is to give you a holistic understanding of
关于机器学习及其运行原理的全面认识 而且我们将
machine learning and how it works and we’re going to be doing this by covering
讲述一系列算法 首先我们将会介绍回归函数然后将
a variety of algorithms so first we’re gonna be covering regression then we’re
进入到分类算法学习中 在这里我们将会介绍knn
going to be moving into classification with k-nearest neighbors and support
和svm算法 然后我们将会进入到聚类算法的学习中 在这里我们将介绍平面聚类
vector machines and then we’re going to get into clustering with flat clustering
和层次聚类 最后我们将会进入到
a hierarchical clustering and then finally we’ll be getting into deep
深度神经网络的学习中
learning with neural networks.
因此 每一阶段将会有一些主要的算法
So, each step of the way with each of the major algorithms
我们将会介绍理论和应用 然后我们将会
we’re going to cover a theory, application and then we’re going to dive
深度探索每一个算法的内部原理
in deep to the inner workings of each of them
因此理论上来说 这是一个高水平的教程
so with theory this is the high-level intuitions it’s actually pretty quick to
可以快速学习所有的算法 大多数的算法实际上
digest the theory of all the algorithms. Most of the algorithms are actually
是相当基础的 因为他们可以用于处理大规模的数据
fairly basic since they need to be able to scale to very large amounts of data.
然后我们将会介绍有关应用 这也是相当快的
Then we move on to application this is also fairly quick
我们将会用到一些包 例如scikit-learn 而且将会把这些算法
we’re going to use a module like scikit-learn and apply these algorithms
应用到真实的数据上 从而了解这些算法是怎么运作的 它期待我们输入什么样的数据
to real-world data to see exactly how they work what kind of input they expect
以及我们期待从这些算法中获得什么样的输出
from us and what kind of output we should expect back from them.
最后我们以一种方式深入探索其内部工作原理 这种方式就是
Then finally we dive into the inner workings in the way that we’re going to do this
从头开始写出这些算法的代码
is by recreating the algorithms themselves from scratch in code
包括所有的数学 当你这样做的时候 你将会
including all the math and all that so when you do this you’ll be able to have
对这些算法如何工作有一个真正完全的理解 这将
a truly complete understanding of how these algorithms work which is going to
帮你静下心来学习
help you down the line
因此 为了跟上这个系列教程 我强烈
So, in order to fall along with a series i strongly
建议你对Python 3有一定的了解 如果你不了解
suggest you at least have the basics of Python 3 down understood if you don’t
我这里也有Python 3的系列基础教程
I do have a Python 3 basics tutorial series here
去看一下这些视频 至少你需要知道
check that out you really just need to get at least to the point where we
用pip命令来安装包
install modules with pip.
知道了这点之后你可以继续学习 但是我认为你真的需要学习Python基础的知识
After that you can continue on but you really need those that initial I think
或许10-15个视频就可以理解Python的核心 我们也将
it’s like maybe 10 or 15 videos of core understanding of Python. We’ll also be
会谈到一些数学知识 但是我们将会谈论这些铺垫
covering a healthy amount of math here but we’ll be talking about the matting
而且当我们需要的时候就会解释的 所以你真的不需要了解太多
and explaining that as we go for sure so you’re not really expected to know much
数学知识
about math
可以解出来大部分代数和几何题目
becoming mostly algebra and geometry that comes up.
机器学习在1950年代被真正的提出来 大约
So, machine learning was really came about in the fifties so like more than a
半个世纪以前 Arthur Samuel创立了该研究领域
half century ago now and it was defined in 1959 by Arthur Samuel as the field of
该领域我们能够赋予机器学习能力而不是
study where we give machines the ability to learn without being explicitly
通过编程去做
programmed to do so.
我有点喜欢这种方式 把知识赋予给
So, the way I kind of like to think of it is it’s in viewing knowledge to a
机器而不通过硬编码 如此的有趣
machine without hard coding that knowledge so interestingly enough when I
当我和那些程序员们 非程序员们交谈的时候 发现
talk to people both programmers and non-programmers and and and find out
他们对机器学习的认识
what they know about machine learning
大多数的人们认为机器学习是硬编码 因此当你问他们
most people think machine learning is hard-coded so when you ask them what’s
机器学习是什么或者它与真正的学习有什么不同
wrong with machine learning or how is it different from actual learning that’s
你会发现大多数人认为机器学习是硬编码 如此有趣的问题
where you find that most people think it’s hard coded so kind of interesting
这个问题是大多数人完全没有意识到这个领域的存在
issue there that most people are completely unaware that this field
而且它也不是硬编码
exists and it’s actually not being hard coded so that was one machine learning
机器学习实际上在1963年被定义 当年弗拉基米尔·万普尼克提出了
was actually kind of defined in 1963 Vladimir Vapnik came up with the support
支持向量机理论(svm)但是这个理论在九十年代前一直被忽视
vector machine but this really went pretty much overlooked until the
前苏联的弗拉基米尔·万普尼克90年代时
90s so Vladimir Vapnik was in the Soviet Union and then in the 90s he
被贝尔实验室从前苏联挖出来 就是那个时候他
was actually scooped out of the Soviet Union by bell labs and that’s when he
证实了支持向量机比神经网络
showed that that the support vector machine was better than the neural
在处理手写字符识别花费的时间更少
network at the time doing handwritten character recognition so it’s
它是我们我所说的手写数字但是无论如何它比支持向量更好
handwritten digits of our call right but anyway it was better than the support
比神经网络更好 在处理这个任务方面 支持向量机
vector a better than the neural network at that task the support vector machines
在时间方面领先很多 直到最近
really took the lead for quite some time really up until very recently when
谷歌重新返回这一领域 投入了很多研究在
Google basically has kind of come back to really put some weight behind the
基于深度学习的神经网络方面
neural network specifically with deep learning.
但是如果你觉得你进入这一领域有点晚
But if you think you’re kind of late to the to the party
对机器学习来说我很确信你
so to speak with machine learning I assure you
不是很晚 我的意思是说 回想下95年代的电脑
you’re not because I mean think about computers in the 95s i mean
我们现在了解
we’re talking
当时刚开始将晶体管放在印刷电路上 把指令集成到你的电脑上
we just started putting transistors on printed circuits instructions to your
那时的电脑一次最多只能处理几位数据那是真的很槽糕 我的意思是
computer was a maximum of a handful of bits at a time so pretty bad i mean even
再回想一下你90年代的电脑
think about your computers in the 90s
即使你是一个博士
this was very hard at
也很难去接触
even if you were like a PhD student is very difficult to even get access to a
一台可以跑大规模支持向量机算法的机器
machine that could run significantly a support vector machine at scale [let’s say].
然而现在我们所生活的时代 你可以在GB或者TB的数据规模上训练
Whereas nowadays we live in a time where you can engage in deep learning with
基于深度学习的神经网络 而且你需要做的
neural networks on like gigabytes or even terabytes of data and what you can
就是把你所知道的价值昂贵的GPU集群搭建在
do is you can spin up a you know hundred-thousand-dollar GPU cluster on
亚马逊的云平台上 你甚至只需要支付少量美金就可以租用一小时
amazon web services and basically just rent it for a few dollars an hour and
然后你就可以使用它们啦
then be done with it
那真是难以置信 我们住在一个难以置信的时代 这是一个最好的时代
that’s incredible like we living an incredible time this is the best time to
我认为我们现在是第一次真正能够
be alive is I think right now is the first time we’ve really been able to
充分学习机器学习的精髓 甚至在某种程度
really stretch and flex the muscles of machine learning up to this point it’s
我们可以学习“机器学习”而不需要“机器”这部分
really been learning without the machine part so we also so much to the point
你可以 你可以使用scikit-learn这个包 而不需要
where like with scikit-learn you can you can use scikit-learn with almost no
理解这个包的原理 你可以使用它 在不改变默认参数情况下
understanding at all you just apply it and you can usually get about
你就能获得大约90%~95%的精度
90~95% accuracy without messing with the default parameter
是的 只使用默认参数就可以 这真的是
yeah you can just get it with the default parameters so that’s also pretty
很疯狂
crazy right
你想要突破限制获得更高的精度
you want to push the limits and get more accuracy out of it then you need to
就需要学习它们的工作原理 以及如何调整这些参数
learn how they work and how you can tweak those parameters so you’re working
如果你打算做自动驾驶方面的研究 想把精度从90%提升到95%
on self-driving car getting 90 to 95% accuracy and
区分一块油污还是毛毯上的小孩
identifying the difference between like a blob of tar and a child in a blanket
那不够好 这需要比更高的精度
that’s not good enough you need much any more accuracy than that
总之 这个系列视频就是为了
so anyway that’s what this series is for is for the people are really looking to
寻求突破界限的人 所以如果你只是想学习
push the limits on what’s available so if you really just want to learn the
一些入门知识 实际上网上已有一些简单的机器学习教程
basics actually already have some simple machine learning tutorials out there for
可以帮你快速上手如何对数据集应用机器学习
just applying machine learning to a dataset you can do this actually very
非常快
very fast.
因此我们将要讲的第一个主题是是回归
So anyways the first topic that we’re gonna be covering is regression and
让我们来深入学习它吧
let’s go ahead and get into it.

发表评论

译制信息
视频概述

机器学习Python实际系列视频的第一讲

听录译者

收集自网络

翻译译者

[B]倔强

审核员

知易行难

视频来源

https://www.youtube.com/watch?v=OGxgnH8y2NM

相关推荐