分类目录归档:机器学习

Springer面向公众开放正版电子书籍,附65本数学、编程、数据挖掘、数据科学、数据分析、机器学习、深度学习、人工智能相关书籍链接及打包下载

施普林格(Springer)是世界著名的科技期刊、图书出版公司,这次疫情期间面向公众免费开放了一批社科人文,自然科学等领域的正版电子书籍(据说是400多本),towardsdatascience 上有学者将其中65本机器学习和数据科学以及统计相关的免费教材下载链接整理了出来,我试了一下,无需注册,可以直接下载相关的PDF书籍,相当方便:Springer has released 65 Machine Learning and Data books for free(https://towardsdatascience.com/springer-has-released-65-machine-learning-and-data-books-for-free-961f8181f189)。 继续阅读

200行写一个自动微分工具

简介

机器学习工具包(PyTorch/TensorFlow)一般都具有自动微分(Automatic Differentiation)机制,微分求解方法包括手动求解法(Manual Differentiation)、数值微分法(Numerical Differentiation)、符号微法(Symbolic Differentiation)、自动微分法(Automatic Differentiation),具体的详细介绍可以参见自动微分(Automatic Differentiation)简介,这里主要说一下自动微分法的实现。

自动微分法实现

github地址:https://github.com/tiandiweizun/autodiff

git上有不少自动微分的实现,如autograd等,这里还有一个特别简单的AutodiffEngine更适合作为教程,但AutodiffEngine是静态图,整个过程对于初学者还是有点复杂的,主要是不直观,于是动手autodiff写了一个简单的动态图的求导,里面的大部分算子的实现还是参照AutodiffEngine的。

设计:其实主要是2个类,一个类Tensor用于保存数据,另一个类OP支持forward和backward,然后各种具体的运算类,如加减乘除等继承OP,然后实现具体的forward和backward过程

过程:分为forward和backward两个过程,forward从前往后计算得到最终的输出,并返回新的tensor(如下图中的v1),新的tensor保存通过哪些子tensor(v-1),哪个具体的算子(ln)计算得到的(计算图),backward按照计算图计算梯度,并赋值给对应的子tensor(v-1)

实现:

先贴一点代码

class Tensor:
    def __init__(self, data, from_tensors=None, op=None, grad=None):
        self.data = data  # 数据
        self.from_tensors = from_tensors  # 是从什么Tensor得到的,保存计算图的历史
        self.op = op  # 操作符运算
        # 梯度
        if grad:
            self.grad = grad
        else:
            self.grad = numpy.zeros(self.data.shape) if isinstance(self.data, numpy.ndarray) else 0
    
    def __add__(self, other):
        # 先判断other是否是常数,然后再调用
        return add.forward([self, other]) if isinstance(other, Tensor) else add_with_const.forward([self, other])

    def backward(self, grad=None):
        # 判断y的梯度是否存在,如果不存在初始化和y.data一样类型的1的数据
        if grad is None:
            self.grad = grad = numpy.ones(self.data.shape) if isinstance(self.data, numpy.ndarray) else 1
        # 如果op不存在,则说明该Tensor为根节点,其from_tensors也必然不存在,否则计算梯度
        if self.op:
            grad = self.op.backward(self.from_tensors, grad)
        if self.from_tensors:
            for i in range(len(grad)):
                tensor = self.from_tensors[i]
                # 把梯度加给对应的子Tensor,因为该Tensor可能参与多个运算
                tensor.grad += grad[i]
                # 子Tensor进行后向过程
                tensor.backward(grad[i])

    # 清空梯度,训练的时候,每个batch应该清空梯度
    def zero_gard(self):
        self.grad = numpy.zeros(self.data.shape) if isinstance(self.data, numpy.ndarray) else 0
class OP:
    def forward(self, from_tensors):
        pass

    def backward(self, from_tensors, grad):
        pass


class Add(OP):
    def forward(self, from_tensors):
        return Tensor(from_tensors[0].data + from_tensors[1].data, from_tensors, self)

    def backward(self, from_tensors, grad):
        return [grad, grad]


add = Add()

这里以加法为例,讲一下具体的实现。

Tensor类有四个属性,分别用于保存数据、子Tensor、操作符、梯度,OP类有两个方法,分别是forward和backword,其中Add类继承OP,实现了具体的forward和backword过程,然后Tensor重载了加法运算,如果是两个Tensor相加,则调用Add内部的forward。

x1_val = 2 * np.ones(3)
x2_val = 3 * np.ones(3)
x1 = Tensor(x1_val)
x2 = Tensor(x2_val)
# x1+x2 调用了Add的forward方法,并用[5,5,5]、x1与x2、加法操作构造新的Tensor,然后赋值给y
y = x1 + x2
assert np.array_equal(y.data, x1_val + x2_val)

backward过程先是计算梯度,然后把梯度赋值给各个子Tensor

# 判断梯度是否存在,此时不存在则初始化为[1,1,1]
# 调用Add的backward计算得到梯度[[1,1,1],[1,1,1]]
# 把梯度累加给对应的子Tensor,并调用x1和x2的backward
# 由于此时梯度存在,则不需要初始化
# 由于x1和x2无op和from_tensors,停止并退出
y.backward()
assert np.array_equal(x1.grad, np.ones_like(x1_val))
assert np.array_equal(x2.grad, np.ones_like(x2_val))

add_with_const和其他运算符参见代码

利用现有的自动求导来训练一个线性回归模型,绝大部分代码来自于AutodiffEngine里面的lr_autodiff.py,其中gen_2d_data方法用于生成数据,每个样例有3维,其中第一维是bias,test_accuracy判断sigmoid(w*x)是否大于0.5来决定分类的类别,并与 y进行对比计算准确率。

我这里仅修改了auto_diff_lr方法,去掉了静态图里面的逻辑,并换成Tensor来封装。

下图为训练日志和训练结果

那些值得推荐和收藏的线性代数学习资源

关于线性代数的重要性,很多做机器学习的同学可能会感同身受,这里引用“牛人林达华推荐有关机器学习的数学书籍”这篇文章中关于线性代数的一段话:

线性代数 (Linear Algebra):

我想国内的大学生都会学过这门课程,但是,未必每一位老师都能贯彻它的精要。这门学科对于Learning是必备的基础,对它的透彻掌握是必不可少的。我在科大一年级的时候就学习了这门课,后来到了香港后,又重新把线性代数读了一遍,所读的是

Introduction to Linear Algebra (3rd Ed.) by Gilbert Strang.

这本书是MIT的线性代数课使用的教材,也是被很多其它大学选用的经典教材。它的难度适中,讲解清晰,重要的是对许多核心的概念讨论得比较透彻。我个人觉得,学习线性代数,最重要的不是去熟练矩阵运算和解方程的方法——这些在实际工作中MATLAB可以代劳,关键的是要深入理解几个基础而又重要的概念:子空间(Subspace),正交(Orthogonality),特征值和特征向量(Eigenvalues and eigenvectors),和线性变换(Linear transform)。从我的角度看来,一本线代教科书的质量,就在于它能否给这些根本概念以足够的重视,能否把它们的联系讲清楚。Strang的这本书在这方面是做得很好的。

而且,这本书有个得天独厚的优势。书的作者长期在MIT讲授线性代数课(18.06),课程的video在MIT的Open courseware网站上有提供。有时间的朋友可以一边看着名师授课的录像,一边对照课本学习或者复习。

https://ocw.mit.edu/courses/mathematics/18-06-linear-algebra-spring-2010/
(注:这里我修正了一下链接,原文链接已经没有了)

那么这里首推的线性代数学习资源就是 Gilbert Strang 教授的这门线性代数课程了,除了上面链接中官方主页的英文原版外,国内网易公开课也早已引进并有同步翻译。

1. 麻省理工公开课:线性代数

http://open.163.com/special/opencourse/daishu.html

课程介绍:

“线性代数”,同微积分一样,是高等数学中两大入门课程之一,不仅是一门非常好的数学课程,也是一门非常好的工具学科,在很多领域都有广泛的用途。它的研 究对象是向量,向量空间(或称线性空间),线性变换和有限维的线性方程组。本课程讲述了矩阵理论及线性代数的基本知识,侧重于那些与其他学科相关的内容, 包括方程组、向量空间、行列式、特征值、相似矩阵及正定矩阵。

课程主讲人:Gilbert Strang 教授

吉尔伯特-斯特朗:1934年11月27日出生,是美国享有盛誉的数学家,在有限元理论、变分法、小波分析及线性代数方面均有所建树。他对教育的贡献尤为 卓著,包括所著有的七部经典数学教材及一部专著。斯特朗自1962年至今担任麻省理工学院教授,其所授课程《线性代数导论》、《计算科学与工程》均在 MIT开放课程软件(MIT OpenCourseWare)中收录,获得广泛好评。

我大概在2013年学习过这门课程,也花了很多时间找这门课程的书籍资源,最终锁定了这本书的第四版英文版电子版:Introduction to Linear Algebra_4ED_Strang ,感兴趣的同学可以关注我们的公众号AINLP,后台回复"xiandai"获取下载链接。

2. 3Blue1Brown: Essence of linear algebra(线性代数的本质)

如果说上面 Gilbert Strang 教授的线性代数课程和书籍都是大部头,那么鼎鼎大名的3Blue1Brown出品的这个线性代数的本质系列视频就是开胃菜,总共14个小视频,视频控制在9-18分钟之间,很适合短时间快速温习。不过这套视频的评价也很高,以下是来自《3Blue1Brown:“线性代数的本质”完整笔记》的点评:

我最早系统地学习线性代数是在大二时候,当时特意选修了学校物理系开设的4学分的线代,大概也就是比我们自己专业的线代多了一章向量空间的内容,其实最后上完发现,整个课程内容还是偏向于计算,对线性代数的几何直觉少有提起,对线性代数的实际运用更是鲜有涉及。同济的那本薄薄的如同九阴真经一般的教材,把线性代数讲的云里雾里,当时一个人在自习教室度过多少不眠之夜,一点一点去思考其概念定理背后的实际意义,多半也是边猜边想,苦不堪言。直到多年以后,有幸在网上听到了MIT的Strang老师开设的线代公开课,才对一些基础概念渐渐明朗,虽然至今又过去了很多年,但是对一些本质的理解,依然清晰。
不过,仔细想想,国内的教材写的云里雾里,才促使了我自发的思考,如果一切得来太容易,也许就不会那么刻骨铭心。我很早之前就想过这个问题,国内的教科书作者简直就是在下一盘大棋,自己出版的书写的高深莫测,翻译国外的书又翻译的含糊曲折,那么留给学生的只有两条路,要么去看原版的英语书,要么就是自己一点点看云雾缭绕的国产书,边猜边想边证明,不管走哪条路,都能走向成功。

最近,在youtube上看到了3Blue1Brown的Essence of linear algebra这门课,有种如获至宝的感觉,整个课程的时间并不长,但是对线性代数的讲解却十分到位,有种浓缩版的Gilbert Strang线代课程的感觉。希望通过这个课程,重温一下Linear Algebra。

这个视频,可以在油管上看官方原版:Essence of linear algebra
也可以在B站上观看:线性代数的本质 - 01 - 向量究竟是什么?
https://www.bilibili.com/video/av5987715/

3. Immersive Linear Algebra

用交互式可视化方法学习数学估计是很多同学梦寐以求的,前两天看到这条微博:

《英文版的线性代数电子书:Immersive Linear Algebra》该书是今天 Hacker News 首页头条。号称是全球第一个全交互式图形的线代电子书。

所以在这里收藏一下,有空的同学可以试一下这个在线学习线性代数的网站,不过看似还有最后两个章节没有完成:http://immersivemath.com/ila/index.html

4. Matrix Algebra for Engineers

http://coursegraph.com/coursera-matrix-algebra-engineers

香港科技大学的面向工程师的矩阵代数(Matrix Algebra for Engineers),该课程介绍的全部是关于矩阵的知识,涵盖了工程师应该知道的线性代数相关知识。学习这门课程的前提是高中数学知识,最好完成了单变量微积分课程之后选修该课程效果更佳。

This course is all about matrices, and concisely covers the linear algebra that an engineer should know. We define matrices and how to add and multiply them, and introduce some special types of matrices. We describe the Gaussian elimination algorithm used to solve systems of linear equations and the corresponding LU decomposition of a matrix. We explain the concept of vector spaces and define the main vocabulary of linear algebra. We develop the theory of determinants and use it to solve the eigenvalue problem. After each video, there are problems to solve and I have tried to choose problems that exemplify the main idea of the lecture. I try to give enough problems for students to solidify their understanding of the material, but not so many that students feel overwhelmed and drop out. I do encourage students to attempt the given problems, but if they get stuck, full solutions can be found in the lecture notes for the course. The mathematics in this matrix algebra course is presented at the level of an advanced high school student, but typically students would take this course after completing a university-level single variable calculus course.

这门课程有个lecture-notes可以直接下载:
http://www.math.ust.hk/~machas/matrix-algebra-for-engineers.pdf

5. Mathematics for Machine Learning: Linear Algebra

http://coursegraph.com/coursera-linear-algebra-machine-learning

伦敦帝国理工学院的 面向机器学习的数学-线性代数课程(Mathematics for Machine Learning: Linear Algebra),这个课程属于Mathematics for Machine Learning Specialization 系列,该系列包含3门子课程,涵盖线性代数,多变量微积分,以及主成分分析(PCA),这个专项系列课程的目标是弥补数学与机器学习以及数据科学鸿沟:Mathematics for Machine Learning。Learn about the prerequisite mathematics for applications in data science and machine learning

In this course on Linear Algebra we look at what linear algebra is and how it relates to vectors and matrices. Then we look through what vectors and matrices are and how to work with them, including the knotty problem of eigenvalues and eigenvectors, and how to use these to solve problems. Finally we look at how to use these to do fun things with datasets - like how to rotate images of faces and how to extract eigenvectors to look at how the Pagerank algorithm works. Since we're aiming at data-driven applications, we'll be implementing some of these ideas in code, not just on pencil and paper. Towards the end of the course, you'll write code blocks and encounter Jupyter notebooks in Python, but don't worry, these will be quite short, focussed on the concepts, and will guide you through if you’ve not coded before. At the end of this course you will have an intuitive understanding of vectors and matrices that will help you bridge the gap into linear algebra problems, and how to apply these concepts to machine learning.

6. 可汗学院公开课:线性代数

http://open.163.com/special/Khan/linearalgebra.html

网易公开课引进翻译的可汗学院线性代数公开课,总共143集,每集短小精悍:

在这个课程里面,主讲者介绍了线性代数的很多内容,包括:矩阵,线性方程组,向量及其运算,向量空间,子空间,零空间,变换,秩与维数,正交化,特征值与特征向量,等等。以上这些内容是线性代数的关键内容,它们也被广泛地应用到现代科学当中。

关于线性代数学习资源,还有很多,这里仅仅抛砖引玉,欢迎大家留言提供线索。

最后,提供一个线性代数学习资源的“大礼包”,包括Gilbert Strang 教授线性代数英文教材第四版电子版,香港科技大学的面向工程师的矩阵代数课程notes,以及从其他地方收集的线性代数网盘资源,感兴趣的同学可以关注我们的公众号AINLP,回复"xiandai"获取:

注:本文首发于课程图谱,转载请注明出处“课程图谱博客”:http://blog.coursegraph.com

本文链接地址:那些值得推荐和收藏的线性代数学习资源 http://blog.coursegraph.com/?p=1014

凸优化及无约束最优化相关资料

很多年前,我的师兄 Jian Zhu 在这里发表过一个系列《无约束最优化》,当时我写下了一段话:

估计有些读者看到这个题目的时候会觉得很数学,和自然语言处理没什么关系,不过如果你听说过最大熵模型、条件随机场,并且知道它们在自然语言处理中被广泛应用,甚至你明白其核心的参数训练算法中有一种叫LBFGS,那么本文就是对这类用于解无约束优化算法的Quasi-Newton Method的初步介绍。

事实上,无论机器学习还是机器学习中的深度学习,数值优化算法都是核心之一,而在这方面,斯坦福大学Stephen Boyd教授等所著的《凸优化》堪称经典:Convex Optimization – Boyd and Vandenberghe ,而且该书的英文电子版在该书主页上可以直接免费下载:

http://web.stanford.edu/~boyd/cvxbook/bv_cvxbook.pdf

还附带了长达301页的Slides:

http://web.stanford.edu/~boyd/cvxbook/bv_cvxslides.pdf

以及额外的练习题、相关代码数据文件:

http://web.stanford.edu/~boyd/cvxbook/bv_cvxbook_extra_exercises.pdf
http://web.stanford.edu/~boyd/cvxbook/cvxbook_additional_exercises/

相当贴心,另外Stephen Boyd教授2014年还在斯坦福大学自家的MOOC平台上开过相关课程: CVX101

https://class.stanford.edu/courses/Engineering/CVX101

提示是:A MOOC on convex optimization, CVX101, was run from 1/21/14 to 3/14/14. If you register for it, you can access all the course materials.

不知道现在注册是否还可以访问课程材料,我当年竟然注册过这门课程,所以还能访问相关资料:

这本书也有中文翻译版,由清华大学出版社出版:

http://www.tup.tsinghua.edu.cn/bookscenter/book_03184902.html

最后提供上述相关材料的打包下载,包括凸优化课程视频、英文原版书籍、练习题和Slides,另外也包括《无约束最优化》的PDF文档,感兴趣的同学可以关注我们的公众号AINLP,回复"youhua"下载:

注:原创文章,转载请注明出处及保留链接“我爱自然语言处理”:https://www.52nlp.cn

本文链接地址:凸优化及无约束最优化相关资料 https://www.52nlp.cn/?p=11222

Geoffrey Hinton 大神面向机器学习的神经网络公开课及相关视频资料

Geoffrey Hinton 大神的"面向机器学习的神经网络(Neural Networks for Machine Learning)"公开课早在2012年就在 Coursera 上开过一轮,之后一直沉寂,直到 Coursera 新课程平台上线,这门经典课程已开过多轮次,之前我们在《深度学习课程资源整理》隆重推荐过。

1月15日,Geoffrey Hinton 大神在twitter上宣布:

My Coursera MOOC "Neural Networks for Machine Learning" was prepared in 2012 and is now seriously out of date so I have asked them to discontinue the course. But the lectures are still a good introduction to many of the basic ideas and are available at https://www.cs.toronto.edu/~hinton/coursera_lectures.html

大意是这门在Coursera上的MOOC课程是在2012年准备的,现在有点过时了,所以要求他们(Coursera)停止提供这门课程。但是这门深度学习课程依然是介绍神经网络相关基础概念的好资料,所以课程视频依然保留在多伦多大学hinton大神的主页下,感兴趣的同学可以直接观看:https://www.cs.toronto.edu/~hinton/coursera_lectures.html

我试了一下Coursera,发现如果之前注册过,还能打开这门课程,但是一旦是非登录状态后,这门课程已经无法在Coursera上找到了:

https://www.coursera.org/learn/neural-networks

这样稍微有点遗憾,不能在Coursera上做相关的Quiz,感兴趣的同学可以参考课程图谱上早期关于这门课程的评论:

http://coursegraph.com/coursera_neuralnets

“宗派大师+开拓者直接讲课,秒杀一切二流子!”

“巨牛级别的人物来开课,我也不说啥了。”

“还有什么好说的呢?Deep Learning必修课程啊!”

该课程最后在Coursera上开课的时间大概在2018年11月份:

http://coursegraph.com/coursera-neural-networks

最后,如果你觉得访问多伦多Hinton教授主页那个教程页面不方便,这里提供早期从Coursera上下载的课程版本,包括视频、PPT、英文字幕等,关注AINLP公众号,回复“hinton"获取:

注:本文首发于“课程图谱博客”:http://blog.coursegraph.com

本文链接地址:Geoffrey Hinton 大神面向机器学习的神经网络公开课及相关视频资料 http://blog.coursegraph.com/?p=985

加速机器学习:从主动学习到BERT和流体标注

知道创宇IA-Lab  岳永鹏

机器学习模型代码优化是为了获得更高效(时间更少、存储更少、计算规模更大)执行的机器指令和具有更强泛化能力的模型,获得更高效执行的机器指令可以采用多核和高频的CPU计算,以及采用并行计算和向量化计算。而获得具有更强泛化能力的模型不仅仅与选择的模型有关,还与标注数据的数量和质量有关。而数据标注需要大量标注人员从事重复而枯燥的工作,这也必然会增加成本。

本文将介绍主动学习(Active Learning)以及主动学习结合Google今年发布的流体标注(Fluid Annotation)和BERT(Bidirectional Encoder Representation from Transformers)对加速机器学习有什么启示。

继续阅读

谷歌云平台上基于TensorFlow的高级机器学习专项课程

Coursera近期推了一门新专项课程:谷歌云平台上基于TensorFlow的高级机器学习专项课程(Advanced Machine Learning with TensorFlow on Google Cloud Platform Specialization),看起来很不错。这个系列包含5门子课程,涵盖端到端机器学习、生产环境机器学习系统、图像理解、面向时间序列和自然语言处理的序列模型、推荐系统等内容,感兴趣的同学可以关注:Learn Advanced Machine Learning with Google Cloud. Build production-ready machine learning models with TensorFlow on Google Cloud Platform.

课程链接:http://coursegraph.com/coursera-specializations-advanced-machine-learning-tensorflow-gcp
继续阅读

Andrew Ng 老师新推的通俗人工智能课程以及其他相关资料

Andrew Ng 老师是我的偶像,他在普及机器学习和深度学习的道路上纵情向前,这不他又在 Coursera 上新推了一门通俗人工智能课程:AI For Everyone(全民AI) :

http://coursegraph.com/coursera-ai-for-everyone

这门课程面向大众进行AI科普,将于2019年年初开课,目前已经可以注册课程。AI不仅适用于工程师,这门非技术性人工智能课程将帮助学习者了解机器学习和深度学习等相关技术,以及将AI应用于自己组织中的问题和机会。 通过这门课程,学习者将会了解当前人工智能可以或者不能做的事情。最后,学习者将了解AI如何影响社会以及我们将如何应对这种技术变革。

AI is not only for engineers. This non-technical course will help you understand technologies like machine learning and deep learning and spot opportunities to apply AI to problems in your own organization. You will see examples of what today’s AI can – and cannot – do. Finally, you will understand how AI is impacting society and how to navigate through this technological change.

If you are a non-technical business leader, “AI for Everyone” will help you understand how to build a sustainable AI strategy. If you are a machine learning engineer or data scientist, this is the course to ask your manager, VP or CEO to take if you want them to understand what you can (and cannot!) do.

继续阅读

Coursera专项课程推荐:金融中的机器学习和强化学习

Coursera近期新推了一个金融和机器学习的专项课程系列:Machine Learning and Reinforcement Learning in Finance Specialization(金融中的机器学习和强化学习),看起来很有意思。

课程链接:http://coursegraph.com/coursera-specializations-machine-learning-reinforcement-finance

这个专项课程的主要目标是为金融相关的机器学习核心范式和算法奠定坚实的基础而提供必要的知识和实战技能,特别关注机器学习在金融投资中不同的实际问题中的应用。

该系列旨在帮助学生解决他们在现实生活中可能遇到的实际的机器学习问题,包括:

(1)将问题映射到可用的机器学习方法的泛化场景,

(2)选择最适合解决问题的特定机器学习方法,以及

(3)成功实施解决方案,并评估其性能。

该专业课程面向三类学生设计:

· 在银行,资产管理公司或对冲基金等金融机构工作的从业人员

· 对将机器学习应用于日内交易感兴趣的个人

· 目前正在攻读金融学,统计学,计算机科学,数学,物理学,工程学或其他相关学科的学位的全日制学生,这些学生希望了解机器学习在金融领域的实际应用。
继续阅读

Coursera上机器学习课程(公开课)汇总推荐

Coursera上有很多机器学习课程,这里做个总结,因为机器学习相关的概念和应用很多,这里推荐的课程仅限于和机器学习直接相关的课程,虽然深度学习属于机器学习范畴,这里暂时也将其排除在外,后续会专门推出深度学习课程的系列推荐。

1. Andrew Ng 老师的 机器学习课程(Machine Learning)

机器学习入门首选课程,没有之一。这门课程从一开始诞生就备受瞩目,据说全世界有数百万人通过这门课程入门机器学习。课程的级别是入门级别的,对学习者的背景要求不高,Andrew Ng 老师讲解的又很通俗易懂,所以强烈推荐从这门课程开始走入机器学习。课程简介:

机器学习是一门研究在非特定编程条件下让计算机采取行动的学科。最近二十年,机器学习为我们带来了自动驾驶汽车、实用的语音识别、高效的网络搜索,让我们对人类基因的解读能力大大提高。当今机器学习技术已经非常普遍,您很可能在毫无察觉情况下每天使用几十次。许多研究者还认为机器学习是人工智能(AI)取得进展的最有效途径。在本课程中,您将学习最高效的机器学习技术,了解如何使用这些技术,并自己动手实践这些技术。更重要的是,您将不仅将学习理论知识,还将学习如何实践,如何快速使用强大的技术来解决新问题。最后,您将了解在硅谷企业如何在机器学习和AI领域进行创新。 本课程将广泛介绍机器学习、数据挖掘和统计模式识别。相关主题包括:(i) 监督式学习(参数和非参数算法、支持向量机、核函数和神经网络)。(ii) 无监督学习(集群、降维、推荐系统和深度学习)。(iii) 机器学习实例(偏见/方差理论;机器学习和AI领域的创新)。课程将引用很多案例和应用,您还需要学习如何在不同领域应用学习算法,例如智能机器人(感知和控制)、文本理解(网络搜索和垃圾邮件过滤)、计算机视觉、医学信息学、音频、数据库挖掘等领域。

这里有老版课程评论,非常值得参考推荐:Machine Learning

2. 台湾大学林轩田老师的 機器學習基石上 (Machine Learning Foundations)---Mathematical Foundations

如果有一定的基础或者学完了Andrew Ng老师的机器学习课程,这门机器学习基石上-数学基础可以作为进阶课程。林老师早期推出的两门机器学习课程口碑和难度均有:机器学习基石机器学习技法 ,现在重组为上和下,非常值得期待:

Machine learning is the study that allows computers to adaptively improve their performance with experience accumulated from the data observed. Our two sister courses teach the most fundamental algorithmic, theoretical and practical tools that any user of machine learning needs to know. This first course of the two would focus more on mathematical tools, and the other course would focus more on algorithmic tools. [機器學習旨在讓電腦能由資料中累積的經驗來自我進步。我們的兩項姊妹課程將介紹各領域中的機器學習使用者都應該知道的基礎演算法、理論及實務工具。本課程將較為著重數學類的工具,而另一課程將較為著重方法類的工具。]

3. 台湾大学林轩田老师的 機器學習基石下 (Machine Learning Foundations)---Algorithmic Foundations

作为2的姊妹篇,这个机器学习基石下-算法基础 更注重机器学习算法相关知识:

Machine learning is the study that allows computers to adaptively improve their performance with experience accumulated from the data observed. Our two sister courses teach the most fundamental algorithmic, theoretical and practical tools that any user of machine learning needs to know. This second course of the two would focus more on algorithmic tools, and the other course would focus more on mathematical tools. [機器學習旨在讓電腦能由資料中累積的經驗來自我進步。我們的兩項姊妹課程將介紹各領域中的機器學習使用者都應該知道的基礎演算法、理論及實務工具。本課程將較為著重方法類的工具,而另一課程將較為著重數學類的工具。

可参考早期的老版本课程评论:機器學習基石 (Machine Learning Foundations) 機器學習技法 (Machine Learning Techniques)

4. 华盛顿大学的 "机器学习专项课程(Machine Learning Specialization)"

这个系列课程包含4门子课程,分别是 机器学习基础:案例研究 , 机器学习:回归 , 机器学习:分类, 机器学习:聚类与检索:

This Specialization from leading researchers at the University of Washington introduces you to the exciting, high-demand field of Machine Learning. Through a series of practical case studies, you will gain applied experience in major areas of Machine Learning including Prediction, Classification, Clustering, and Information Retrieval. You will learn to analyze large and complex datasets, create systems that adapt and improve over time, and build intelligent applications that can make predictions from data.

4.1 Machine Learning Foundations: A Case Study Approach(机器学习基础: 案例研究)

你是否好奇数据可以告诉你什么?你是否想在关于机器学习促进商业的核心方式上有深层次的理解?你是否想能同专家们讨论关于回归,分类,深度学习以及推荐系统的一切?在这门课上,你将会通过一系列实际案例学习来获取实践经历。

Do you have data and wonder what it can tell you? Do you need a deeper understanding of the core ways in which machine learning can improve your business? Do you want to be able to converse with specialists about anything from regression and classification to deep learning and recommender systems? In this course, you will get hands-on experience with machine learning from a series of practical case-studies. At the end of the first course you will have studied how to predict house prices based on house-level features, analyze sentiment from user reviews, retrieve documents of interest, recommend products, and search for images. Through hands-on practice with these use cases, you will be able to apply machine learning methods in a wide range of domains. This first course treats the machine learning method as a black box. Using this abstraction, you will focus on understanding tasks of interest, matching these tasks to machine learning tools, and assessing the quality of the output. In subsequent courses, you will delve into the components of this black box by examining models and algorithms. Together, these pieces form the machine learning pipeline, which you will use in developing intelligent applications. Learning Outcomes: By the end of this course, you will be able to: -Identify potential applications of machine learning in practice. -Describe the core differences in analyses enabled by regression, classification, and clustering. -Select the appropriate machine learning task for a potential application. -Apply regression, classification, clustering, retrieval, recommender systems, and deep learning. -Represent your data as features to serve as input to machine learning models. -Assess the model quality in terms of relevant error metrics for each task. -Utilize a dataset to fit a model to analyze new data. -Build an end-to-end application that uses machine learning at its core. -Implement these techniques in Python.

4.2 Machine Learning: Regression(机器学习: 回归问题)

这门课程关注机器学习里面的一个基本问题: 回归(Regression), 也通过案例研究(预测房价)的方式进行回归问题的学习,最终通过Python实现相关的机器学习算法。

Case Study - Predicting Housing Prices In our first case study, predicting house prices, you will create models that predict a continuous value (price) from input features (square footage, number of bedrooms and bathrooms,...). This is just one of the many places where regression can be applied. Other applications range from predicting health outcomes in medicine, stock prices in finance, and power usage in high-performance computing, to analyzing which regulators are important for gene expression. In this course, you will explore regularized linear regression models for the task of prediction and feature selection. You will be able to handle very large sets of features and select between models of various complexity. You will also analyze the impact of aspects of your data -- such as outliers -- on your selected models and predictions. To fit these models, you will implement optimization algorithms that scale to large datasets. Learning Outcomes: By the end of this course, you will be able to: -Describe the input and output of a regression model. -Compare and contrast bias and variance when modeling data. -Estimate model parameters using optimization algorithms. -Tune parameters with cross validation. -Analyze the performance of the model. -Describe the notion of sparsity and how LASSO leads to sparse solutions. -Deploy methods to select between models. -Exploit the model to form predictions. -Build a regression model to predict prices using a housing dataset. -Implement these techniques in Python.

4.3 Machine Learning: Classification(机器学习:分类问题)

这门课程关注机器学习里面的另一个基本问题: 分类(Classification), 通过两个案例研究进行学习:情感分析和贷款违约预测,最终通过Python实现相关的算法(也可以选择其他语言,但是强烈推荐Python)。

Case Studies: Analyzing Sentiment & Loan Default Prediction In our case study on analyzing sentiment, you will create models that predict a class (positive/negative sentiment) from input features (text of the reviews, user profile information,...). In our second case study for this course, loan default prediction, you will tackle financial data, and predict when a loan is likely to be risky or safe for the bank. These tasks are an examples of classification, one of the most widely used areas of machine learning, with a broad array of applications, including ad targeting, spam detection, medical diagnosis and image classification. In this course, you will create classifiers that provide state-of-the-art performance on a variety of tasks. You will become familiar with the most successful techniques, which are most widely used in practice, including logistic regression, decision trees and boosting. In addition, you will be able to design and implement the underlying algorithms that can learn these models at scale, using stochastic gradient ascent. You will implement these technique on real-world, large-scale machine learning tasks. You will also address significant tasks you will face in real-world applications of ML, including handling missing data and measuring precision and recall to evaluate a classifier. This course is hands-on, action-packed, and full of visualizations and illustrations of how these techniques will behave on real data. We've also included optional content in every module, covering advanced topics for those who want to go even deeper! Learning Objectives: By the end of this course, you will be able to: -Describe the input and output of a classification model. -Tackle both binary and multiclass classification problems. -Implement a logistic regression model for large-scale classification. -Create a non-linear model using decision trees. -Improve the performance of any model using boosting. -Scale your methods with stochastic gradient ascent. -Describe the underlying decision boundaries. -Build a classification model to predict sentiment in a product review dataset. -Analyze financial data to predict loan defaults. -Use techniques for handling missing data. -Evaluate your models using precision-recall metrics. -Implement these techniques in Python (or in the language of your choice, though Python is highly recommended).

4.4 Machine Learning: Clustering & Retrieval(机器学习:聚类和检索)

这门课程关注的是机器学习里面的另外两个基本问题:聚类和检索,同样通过案例研究进行学习:相似文档查询,一个非常具有实际应用价值的问题:

Case Studies: Finding Similar Documents A reader is interested in a specific news article and you want to find similar articles to recommend. What is the right notion of similarity? Moreover, what if there are millions of other documents? Each time you want to a retrieve a new document, do you need to search through all other documents? How do you group similar documents together? How do you discover new, emerging topics that the documents cover? In this third case study, finding similar documents, you will examine similarity-based algorithms for retrieval. In this course, you will also examine structured representations for describing the documents in the corpus, including clustering and mixed membership models, such as latent Dirichlet allocation (LDA). You will implement expectation maximization (EM) to learn the document clusterings, and see how to scale the methods using MapReduce. Learning Outcomes: By the end of this course, you will be able to: -Create a document retrieval system using k-nearest neighbors. -Identify various similarity metrics for text data. -Reduce computations in k-nearest neighbor search by using KD-trees. -Produce approximate nearest neighbors using locality sensitive hashing. -Compare and contrast supervised and unsupervised learning tasks. -Cluster documents by topic using k-means. -Describe how to parallelize k-means using MapReduce. -Examine probabilistic clustering approaches using mixtures models. -Fit a mixture of Gaussian model using expectation maximization (EM). -Perform mixed membership modeling using latent Dirichlet allocation (LDA). -Describe the steps of a Gibbs sampler and how to use its output to draw inferences. -Compare and contrast initialization techniques for non-convex optimization objectives. -Implement these techniques in Python.

5. 密歇根大学的 Applied Machine Learning in Python(在Python中应用机器学习)

Python机器学习应用课程,这门课程主要聚焦在通过Python应用机器学习,包括机器学习和统计学的区别,机器学习工具包scikit-learn的介绍,有监督学习和无监督学习,数据泛化问题(例如交叉验证和过拟合)等。这门课程同时属于"Python数据科学应用专项课程系列(Applied Data Science with Python Specialization)"。

This course will introduce the learner to applied machine learning, focusing more on the techniques and methods than on the statistics behind these methods. The course will start with a discussion of how machine learning is different than descriptive statistics, and introduce the scikit learn toolkit. The issue of dimensionality of data will be discussed, and the task of clustering data, as well as evaluating those clusters, will be tackled. Supervised approaches for creating predictive models will be described, and learners will be able to apply the scikit learn predictive modelling methods while understanding process issues related to data generalizability (e.g. cross validation, overfitting). The course will end with a look at more advanced techniques, such as building ensembles, and practical limitations of predictive models. By the end of this course, students will be able to identify the difference between a supervised (classification) and unsupervised (clustering) technique, identify which technique they need to apply for a particular dataset and need, engineer features to meet that need, and write python code to carry out an analysis. This course should be taken after Introduction to Data Science in Python and Applied Plotting, Charting & Data Representation in Python and before Applied Text Mining in Python and Applied Social Analysis in Python.

6. 俄罗斯国立高等经济学院和Yandex联合推出的 高级机器学习专项课程系列(Advanced Machine Learning Specialization)

该系列授课语言为英语,包括深度学习,Kaggle数据科学竞赛,机器学习中的贝叶斯方法,强化学习,计算机视觉,自然语言处理等7门子课程,截止目前前3门课程已开,感兴趣的同学可以关注:

This specialization gives an introduction to deep learning, reinforcement learning, natural language understanding, computer vision and Bayesian methods. Top Kaggle machine learning practitioners and CERN scientists will share their experience of solving real-world problems and help you to fill the gaps between theory and practice. Upon completion of 7 courses you will be able to apply modern machine learning methods in enterprise and understand the caveats of real-world data and settings.

以下是和机器学习直接相关的子课程,其他这里略过:

6.3 Bayesian Methods for Machine Learning(面向机器学习的贝叶斯方法)

该课程关注机器学习中的贝叶斯方法,贝叶斯方法在很多领域都很有用,例如游戏开发和毒品发现。它们给很多机器学习算法赋予了“超能力”,例如处理缺失数据,从小数据集中提取大量有用的信息等。当贝叶斯方法被应用在深度学习中时,它可以让你将模型压缩100倍,并且自动帮你调参,节省你的时间和金钱。

Bayesian methods are used in lots of fields: from game development to drug discovery. They give superpowers to many machine learning algorithms: handling missing data, extracting much more information from small datasets. Bayesian methods also allow us to estimate uncertainty in predictions, which is a really desirable feature for fields like medicine. When Bayesian methods are applied to deep learning, it turns out that they allow you to compress your models 100 folds, and automatically tune hyperparametrs, saving your time and money. In six weeks we will discuss the basics of Bayesian methods: from how to define a probabilistic model to how to make predictions from it. We will see how one can fully automate this workflow and how to speed it up using some advanced techniques. We will also see applications of Bayesian methods to deep learning and how to generate new images with it. We will see how new drugs that cure severe diseases be found with Bayesian methods.

7. 约翰霍普金斯大学的 Practical Machine Learning(机器学习实战)

这门课程从数据科学的角度来应用机器学习进修实战,课程将会介绍机器学习的基础概念譬如训练集,测试集,过拟合和错误率等,同时这门课程也会介绍机器学习的基本模型和算法,例如回归,分类,朴素贝叶斯,以及随机森林。这门课程最终会覆盖一个完整的机器学习实战周期,包括数据采集,特征生成,机器学习算法应用以及结果评估等。这门机器学习实践课程同时属于约翰霍普金斯大学的 数据科学专项课程(Data Science Specialization)系列:

One of the most common tasks performed by data scientists and data analysts are prediction and machine learning. This course will cover the basic components of building and applying prediction functions with an emphasis on practical applications. The course will provide basic grounding in concepts such as training and tests sets, overfitting, and error rates. The course will also introduce a range of model based and algorithmic machine learning methods including regression, classification trees, Naive Bayes, and random forests. The course will cover the complete process of building prediction functions including data collection, feature creation, algorithms, and evaluation.

8. 卫斯理大学 Regression Modeling in Practice(回归模型实战)

这门课程关注的是数据分析以及机器学习领域的最重要的一个概念和工具:回归(模型)分析。这门课程使用SAS或者Python,从线性回归开始学习,到了解整个回归模型,以及应用回归模型进行数据分析:

This course focuses on one of the most important tools in your data analysis arsenal: regression analysis. Using either SAS or Python, you will begin with linear regression and then learn how to adapt when two variables do not present a clear linear relationship. You will examine multiple predictors of your outcome and be able to identify confounding variables, which can tell a more compelling story about your results. You will learn the assumptions underlying regression analysis, how to interpret regression coefficients, and how to use regression diagnostic plots and other tools to evaluate the quality of your regression model. Throughout the course, you will share with others the regression models you have developed and the stories they tell you.

这门课程同时属于卫斯理大学的 数据分析与解读专项课程系列(Data Analysis and Interpretation Specialization)

9. 卫斯理大学的 Machine Learning for Data Analysis(面向数据分析的机器学习)

这门课程关注数据分析里的机器学习,机器学习的过程是一个开发、测试和应用预测算法来实现目标的过程,这门课程以 Regression Modeling in Practice(回归模型实战) 为基础,介绍机器学习中的有监督学习概念,同时从基础的分类算法到决策树以及聚类都会覆盖。通过完成这门课程,你将会学习如何应用、测试和解读机器学习算法用来解决实际问题。

Are you interested in predicting future outcomes using your data? This course helps you do just that! Machine learning is the process of developing, testing, and applying predictive algorithms to achieve this goal. Make sure to familiarize yourself with course 3 of this specialization before diving into these machine learning concepts. Building on Course 3, which introduces students to integral supervised machine learning concepts, this course will provide an overview of many additional concepts, techniques, and algorithms in machine learning, from basic classification to decision trees and clustering. By completing this course, you will learn how to apply, test, and interpret machine learning algorithms as alternative methods for addressing your research questions.

这门课程同时属于卫斯理大学的 数据分析与解读专项课程系列(Data Analysis and Interpretation Specialization)

10. 加州大学圣地亚哥分校的 Machine Learning With Big Data(大数据机器学习)

这门课程关注大数据中的机器学习技术,将会介绍相关的机器学习算法和工具。通过这门课程,你可以学到:通过机器学习过程来设计和利用数据;将机器学习技术用于探索和准备数据来建模;识别机器学习问题的类型;通过广泛可用的开源工具来使用数据构建模型;在Spark中使用大规模机器学习算法分析大数据。

Want to make sense of the volumes of data you have collected? Need to incorporate data-driven decisions into your process? This course provides an overview of machine learning techniques to explore, analyze, and leverage data. You will be introduced to tools and algorithms you can use to create machine learning models that learn from data, and to scale those models up to big data problems. At the end of the course, you will be able to: • Design an approach to leverage data using the steps in the machine learning process. • Apply machine learning techniques to explore and prepare data for modeling. • Identify the type of machine learning problem in order to apply the appropriate set of techniques. • Construct models that learn from data using widely available open source tools. • Analyze big data problems using scalable machine learning algorithms on Spark.

这门课程同时属于 加州大学圣地亚哥分校的大数据专项课程系列(Big Data Specialization)

11. 俄罗斯搜索巨头Yandex推出的 Big Data Applications: Machine Learning at Scale(大数据应用:大规模机器学习)

机器学习正在改变世界,通过这门课程,你将会学习到:识别实战中需要用机器学习算法解决的问题;通过Spark MLLib构建、调参、和应用线性模型;里面文本处理的方法;用决策树和Boost方法解决机器学习问题;构建自己的推荐系统。

Machine learning is transforming the world around us. To become successful, you’d better know what kinds of problems can be solved with machine learning, and how they can be solved. Don’t know where to start? The answer is one button away. During this course you will: - Identify practical problems which can be solved with machine learning - Build, tune and apply linear models with Spark MLLib - Understand methods of text processing - Fit decision trees and boost them with ensemble learning - Construct your own recommender system. As a practical assignment, you will - build and apply linear models for classification and regression tasks; - learn how to work with texts; - automatically construct decision trees and improve their performance with ensemble learning; - finally, you will build your own recommender system! With these skills, you will be able to tackle many practical machine learning tasks. We provide the tools, you choose the place of application to make this world of machines more intelligent.

这门课程同时属于Yandex推出的 面向数据工程师的大数据专项课程系列(Big Data for Data Engineers Specialization)

注:本文首发“课程图谱博客”:http://blog.coursegraph.com ,同步发布到这里, 本文链接地址:http://blog.coursegraph.com/coursera上机器学习课程公开课汇总推荐 http://blog.coursegraph.com/?p=696