2019机器学习比赛
With strong roots in statistics, Machine Learning is becoming one of the most interesting and fast-paced computer science fields to work in. There’s an endless supply of industries and applications machine learning can be applied to to make them more efficient and intelligent.
凭借强大的统计基础，机器学习正成为最有趣且发展最快的计算机科学领域之一。机器和应用的源源不绝，可以应用机器学习来提高它们的效率和智能性。
Chat bots, spam filtering, ad serving, search engines, and fraud detection, are among just a few examples of how machine learning models underpin everyday life. Machine learning is what lets us find patterns and create mathematical models for things that would sometimes be impossible for humans to do.
聊天机器人，垃圾邮件过滤，广告投放，搜索引擎和欺诈检测只是机器学习模型如何支撑日常生活的几个例子。 机器学习使我们能够找到模式并为有时人类无法做到的事情创建数学模型。
Unlike data science courses, which contain topics like exploratory data analysis, statistics, communication, and visualization techniques, machine learning courses focus on teaching only the machine learning algorithms, how they work mathematically, and how to utilize them in a programming language.
与包含探索性数据分析，统计，通信和可视化技术等主题的数据科学课程不同，机器学习课程专注于仅教授机器学习算法，它们如何进行数学运算以及如何在编程语言中加以利用。
Now, it’s time to get started. Here’s a quick recap of the top five machine learning courses this year.
现在，该开始了。 这是今年前五名机器学习课程的快速回顾。
TL; DR (TL;DR)
The best five machine learning courses:
最好的五门机器学习课程：
什么才是真正好的机器学习课程？ (What makes a really good machine learning course?)
After several years of following the e-learning landscape and enrolling in countless machine learning courses from various platforms, like Coursera, Edx, Udemy, Udacity, and DataCamp, I’ve collected the best machine learning courses currently available.
跟随电子学习领域的几年，并从Coursera，Edx，Udemy，Udacity和DataCamp等各种平台注册了无数机器学习课程之后，我收集了当前可用的最佳机器学习课程。
标准 (Criteria)
Each course in the list is subject to the following criteria.The course should:
列表中的每门课程均应符合以下条件。该课程应：
- Strictly focus on machine learning 严格专注于机器学习
- Use free, open-source programming languages, namely Python, R, or Octave 使用免费的开源编程语言，即Python，R或Octave
- Use free, open-source libraries for those languages. Some instructors and providers use commercial packages, so these courses are removed from consideration. 对这些语言使用免费的开源库。 一些讲师和提供者使用商业软件包，因此将这些课程从考虑中删除。
- Contain programming assignments for practice and hands-on experience 包含编程练习和实践经验
- Explain how the algorithms work mathematically 解释算法如何在数学上起作用
- Be self-paced, on-demand or available every month or so 自定进度，按需或每个月左右有空
- Have engaging instructors and interesting lectures 有引人入胜的讲师和有趣的讲座
- Have above average ratings and reviews from various aggregators and forums 各个聚合器和论坛的评分和评论均高于平均水平
With that, the overall pool of courses gets culled down quickly, but the goal is to help you decide on a course that’s worth your time and energy.
这样一来，整个课程库就会Swift被淘汰，但目标是帮助您选择值得您花费时间和精力的课程。
To immerse yourself and learn ML as fast and comprehensively as possible, I believe you should also seek out various books in addition to your online learning. Below are two books that made a big impact to my learning experience, and remain at an arm’s length at all times.
为了使自己沉浸其中并尽可能快速而全面地学习ML，我相信除了在线学习外，您还应该查找各种书籍。 以下两本书对我的学习经历产生了重大影响，并且始终与我保持距离。
两个优秀的书友 (Two Excellent Book Companions)
In addition to taking any of the video courses below, if you’re fairly new to machine learning you should consider reading the following books:
除了学习以下任何视频课程之外，如果您还不熟悉机器学习，还应该考虑阅读以下书籍：
Introduction to Statistical Learning, which is also available for Free online.
This book has incredibly clear and straightforward explanations and examples to boost your overall mathematical intuition for many of the fundamental machine learning techniques. This book is more on the theory side of things, but it does contain many exercises and examples using the R programming language.
本书提供了非常清晰明了的解释和示例，可以帮助您提高许多基本机器学习技术的整体数学直觉。 本书更多是在理论方面，但是它确实包含许多使用R编程语言的练习和示例。
Hands-On Machine Learning with Scikit-Learn and TensorFlow, also available through a Safari subscription
A good complement to the previous book since this text focuses more on the application of machine learning using Python. Together with any of the courses below, this book will reinforce your programming skills and show you how to apply machine learning to projects immediately.
这是上一本书的很好的补充，因为本文将重点更多地放在使用Python的机器学习中。 本书与以下任何课程一起，将增强您的编程技能，并向您展示如何将机器学习立即应用于项目。
Now, let’s get to the course descriptions and reviews.
现在，让我们进入课程说明和评论。
1 机器学习— Coursera (1 Machine Learning — Coursera)
This is the course for which all other machine learning courses are judged. The teacher and creator of this course for beginners is Andrew Ng, a Stanford professor, co-founder of Google Brain, co-founder of Coursera, and the VP that grew Baidu’s AI team to thousands of scientists.
这是对所有其他机器学习课程的评判。 该课程的初学者和创建者是史丹佛大学教授，谷歌大脑的共同创始人，库斯拉的共同创始人安德鲁·伍(Andrew Ng)，他是将百度的AI团队发展为成千上万科学家的副总裁。
The course uses the open-source programming language Octave instead of Python or R for the assignments. This might be a deal-breaker for some, but if you’re a complete beginner, Octave is actually a simple way to learn the fundamentals of ML.
本课程使用开放源代码编程语言Octave代替Python或R进行作业。 对于某些人来说，这可能是一个折衷方案，但是如果您是一个完整的初学者，Octave实际上是学习ML基础的一种简单方法。
Overall, the course material is extremely well-rounded and intuitively articulated by Ng. All of the math required to understand each algorithm is completely explained, with some calculus explanations and a refresher for Linear Algebra. The course is fairly self-contained, but some knowledge of Linear Algebra beforehand would definitely help.
总体而言，Ng对该课程的材料进行了非常全面和直观的阐述。 完整解释了理解每种算法所需的所有数学，并提供了一些演算说明和线性代数的复习课程。 该课程相当完备，但是事先掌握线性代数知识肯定会有所帮助。
Provider: Andrew Ng, StanfordCost: Free to audit, $79 for Certificate
提供商： Andrew Ng，斯坦福大学费用：免费审核，证书$ 79
Course structure:
课程结构：
- Linear Regression with One Variable 一变量线性回归
- Linear Algebra Review 线性代数复习
- Linear Regression with Multiple Variables 多元线性回归
- Octave/Matlab Tutorial 八度/ Matlab教程
- Logistic Regression 逻辑回归
- Regularization 正则化
- Neural Networks: Representation 神经网络：表示
- Neural Networks: Learning 神经网络：学习
- Advice for Applying Machine Learning 应用机器学习的建议
- Machine Learning System Design 机器学习系统设计
- Support Vector Machines 支持向量机
- Dimensionality Reduction 降维
- Anomaly Detection 异常检测
- Recommender Systems 推荐系统
- Large Scale Machine Learning 大规模机器学习
- Application Example: Photo OCR 应用示例：照片OCR
All of this is covered over eleven weeks. If you can commit to completing the whole course, you’ll have a good base knowledge of machine learning in about four months.
所有这一切都涵盖了十一周。 如果您愿意完成整个课程，那么您将在大约四个月的时间里拥有良好的机器学习基础知识。
After that, you can comfortably move on to a more advanced or specialized topic, like Deep Learning, ML Engineering, or anything else that piques your interest.
之后，您可以轻松地进入更高级或更专业的主题，例如深度学习，机器学习工程或其他引起您兴趣的主题。
This is undoubtedly the best course to start with as newcomer.
毫无疑问，这是最好的入门课程。
2 深度学习专业化— Coursera (2 Deep Learning Specialization — Coursera)
Also taught by Andrew Ng, this specialization is a more advanced course series for anyone interested in learning about neural networks and Deep Learning, and how they solve many problems.
同样由安德鲁·伍(Andrew Ng)教授的，该专业课程是面向对神经网络和深度学习以及它们如何解决许多问题感兴趣的人士的更高级课程系列。
The assignments and lectures in each course utilize the Python programming language and use the TensorFlow library for neural networks. This is naturally a great follow up to Ng’s Machine Learning course since you’ll receive a similar lecture style but now will be exposed to using Python for machine learning.
每门课程中的作业和讲座均使用Python编程语言，并将TensorFlow库用于神经网络。 这自然是Ng机器学习课程的一个很好的后续课程，因为您将获得类似的演讲风格，但是现在将接触使用Python进行机器学习。
Provider: Andrew Ng, deeplearning.aiCost: Free to audit, $49/month for Certificate
提供商： Andrew Ng，deeplearning.ai 费用：免费审核，证书每月49美元
Courses:
培训班：
Neural Networks and Deep Learning
神经网络与深度学习
- Introduction to Deep Learning 深度学习导论
- Neural Network Basics 神经网络基础
- Shallow Neural Networks 浅层神经网络
- Deep Neural Networks 深度神经网络
2. Improving Neural Networks: Hyperparameter Tuning, Regularization, and Optimization
2.改善神经网络：超参数调整，正则化和优化
- Practical Aspects of Deep Learning 深度学习的实践方面
- Optimization Algorithms 优化算法
- Hyperparameter Tuning, Batch Normalization and Programming Frameworks 超参数调整，批处理规范化和编程框架
3. Structuring Machine Learning Projects
3.构建机器学习项目
- ML Strategy (1) ML策略(1)
- ML Strategy (2) 机器学习策略(2)
4. Convolutional Neural Networks
4.卷积神经网络
- Foundations of Convolutional Neural Networks 卷积神经网络的基础
- Deep Convolutional Models: Case Studies 深度卷积模型：案例研究
- Object Detection 物体检测
- Special Applications: Face Recognition and Neural Style Transfer 特殊应用：人脸识别和神经风格转换
5. Sequence Models
5.序列模型
- Recurrent Neural Networks 递归神经网络
- Natural Language Processing and Word Embeddings 自然语言处理和词嵌入
- Sequence Models and Attention Mechanism 序列模型和注意机制
In order to understand the algorithms presented in this course, you should already be familiar with Linear Algebra and machine learning in general. If you need some suggestions for where to pick up the math required, see the Learning Guide towards the end of this article.
为了理解本课程中介绍的算法，您应该已经基本熟悉线性代数和机器学习。 如果您需要一些有关在何处获取所需数学知识的建议，请参阅本文末尾的《学习指南》。
3 使用Python进行机器学习— Coursera (3 Machine Learning with Python — Coursera)
Another beginner course, this one focuses solely on the most fundamental machine learning algorithms. The instructor, slide animations, and explanation of the algorithms combine very nicely to give you an intuitive feel for the basics.
另一门初学者课程，仅专注于最基本的机器学习算法。 讲师，幻灯片动画和算法说明很好地结合在一起，使您对基础知识有了直观的感觉。
This course uses Python and is somewhat lighter on the mathematics behind the algorithms. With each module you’ll get a chance to spool up an interactive Jupyter notebook in your browser to work through the new concepts you just learned. Each notebook reinforces your knowledge and gives you concrete instructions for using an algorithm on real data.
本课程使用Python，并且对算法背后的数学内容有所简化。 使用每个模块，您将有机会在浏览器中创建一个交互式Jupyter笔记本，以浏览刚刚学到的新概念。 每个笔记本都可以增强您的知识，并为您提供有关在实际数据上使用算法的具体说明。
Provider: IBM, Cognitive ClassPrice: Free to audit, $39/month for Certificate
提供者： IBM，认知类价格：免费审核，证书每月39美元
Course structure:
课程结构：
- Intro to Machine Learning 机器学习入门
- Regression 回归
- Classification 分类
- Clustering 聚类
- Recommender Systems 推荐系统
- Final Project 最终项目
One of the best things about this course is the practical advice given for each algorithm. When introduced to a new algorithm, the instructor provides you with how it works, its pros and cons, and what sort of situations you should use it in. These points are often left out of other courses and this information is important for new learners to understand the broader context.
这门课程最好的事情之一就是为每种算法提供实用建议。 当介绍一种新算法时，讲师会为您提供它的工作原理，优缺点以及应在何种情况下使用它。这些知识通常不在其他课程中，这些信息对于新学习者来说非常重要。了解更广泛的背景。
4 高级机器学习专业化— Coursera (4 Advanced Machine Learning Specialization — Coursera)
This is another advanced series of courses that casts a very wide net. If you have an interest in covering as many machine learning techniques as possible, this Specialization the key to a balanced and extensive online curriculum.
这是另一套高级课程，涵盖了非常广泛的网络。 如果您有兴趣涵盖尽可能多的机器学习技术，那么本专业课程是平衡和广泛的在线课程的关键。
The instruction in this course is fantastic: extremely well-presented and concise. Due to its advanced nature, you will need more math than any of the other courses listed so far. If you have already taken a beginner course and brushed up on linear algebra and calculus, this is a good choice to fill out the rest of your machine learning expertise.
本课程中的说明非常棒：非常简洁明了。 由于其先进的性质，您将需要的数学比到目前为止列出的其他任何课程都要多。 如果您已经学习过入门课程，并且已经学习过线性代数和微积分，那么这是填补其余机器学习专长的不错的选择。
Much of what’s covered in this Specialization is pivotal to many machine learning projects.
本专业知识涵盖的大部分内容对于许多机器学习项目都是至关重要的。
Provider: National Research University Higher School of EconomicsCost: Free to audit, $49/month for Certificate
提供商：国立研究大学经济学院费用：免费审核，证书每月49美元
Courses:
培训班：
Introduction to Deep Learning
深度学习导论
- Intro to Optimization 优化介绍
- Intro to Neural Networks 神经网络简介
- Deep Learning for Images 图像深度学习
- Unsupervised Representation Learning 无监督表示学习
- Dee Learning for Sequences 迪伊学习序列
- Final Project 最终项目
2. How to Win Data Science Competitions: Learn from Top Kagglers
2.如何赢得数据科学竞赛：向顶级Kagglers学习
- Intro and Recap 介绍和回顾
- Feature Processing and Generation with Respect to Models 有关模型的特征处理和生成
- Final Project Description 最终项目说明
- Exploratory Data Analysis 探索性数据分析
- Validation 验证方式
- Data Leakages 资料泄漏
- Metrics Optimization 指标优化
- Advanced Feature Engineering 1 高级功能工程1
- Hyperparameter Optimization 超参数优化
- Advanced Feature Engineering 2 高级功能工程2
- Ensembling 组装
- Competitions Go Through 比赛进行
- Final Project 最终项目
3. Bayesian Methods for Machine Learning
3.机器学习的贝叶斯方法
- Intro to Bayesian Methods and Conjugate Priors 贝叶斯方法简介和共轭先验
- Expectation-Maximization Algorithm 期望最大化算法
- Variational Inference and Latent Dirichlet Allocation (LDA) 变分推理和潜在狄利克雷分配(LDA)
- Markov Chain Monte Carlo 马尔可夫链蒙特卡洛
- Variational Autoencoder 可变自动编码器
- Gaussian Processes and Bayesian Optimization 高斯过程和贝叶斯优化
- Final Project 最终项目
4. Practical Reinforcement Learning
4.实用强化学习
- Intro: Why Should I Care? 简介：我为什么要关心？
- At the Heart of RL: Dynamic Programming RL的核心：动态编程
- Model-Free Methods 无模型方法
- Approximate Value Based Methods 基于近似值的方法
- Policy-based Methods 基于策略的方法
- Exploration 勘探
5. Deep Learning in Computer Vision
5.计算机视觉中的深度学习
- Intro to Image Processing and Computer Vision 图像处理和计算机视觉入门
- Convolutional Features for Visual Recognition 视觉识别的卷积特征
- Object Detection 物体检测
- Object Tracking and Action Recognition 对象跟踪和动作识别
- Image Segmentation and Synthesis 图像分割与合成
6. Natural Language Processing
6.自然语言处理
- Intro and Text Classification 简介和文字分类
- Language Modeling and Sequence Tagging 语言建模和序列标记
- Vector Space Models of Semantics 语义向量空间模型
- Sequence to Sequence Tasks 序列到序列任务
- Dialog Systems 对话系统
7. Addressing the Large Hadron Collider Challenges by Machine Learning
7.通过机器学习应对大型强子对撞机挑战
- Intro to Particle Physics for Data Scientists 数据科学家粒子物理学入门
- Particle Identification 颗粒识别
- Search for New Physics in Rare Decays 在稀有衰变中搜索新物理
- Search for Dark Matter Hints with Machine Learning at New CERN Experiment 在新的CERN实验中使用机器学习搜索暗物质提示
- Detector Optimization 检测器优化
It takes about 8–10 months to complete this series of courses, so if you start today, in a little under a year you’ll have learned a massive amount of machine learning and be able to start tackling more cutting-edge applications.
完成这一系列课程大约需要8到10个月，因此，如果您从今天开始，不到一年的时间，您将学到大量的机器学习知识，并且能够开始处理更多的前沿应用程序。
Throughout the months, you will also be creating several real projects that result in a computer learning how to read, see, and play. These projects will be great candidates for your portfolio and will result in your GitHub looking very active to any interested employers.
在过去的几个月中，您还将创建多个真实的项目，这些项目将使计算机学习如何阅读，观看和玩耍。 这些项目将是您投资组合的最佳候选人，并使您的GitHub对于任何感兴趣的雇主而言都非常活跃。
5 机器学习— EdX (5 Machine Learning — EdX)
This is an advanced course that has the highest math prerequisite out of any other course in this list. You’ll need a very firm grasp of Linear Algebra, Calculus, Probability, and programming. The course has interesting programming assignments in either Python or Octave, but the course doesn’t teach either language.
这是一门高级课程，其数学先决条件比该列表中的其他任何课程都要高。 您需要非常牢固地掌握线性代数，微积分，概率和编程。 该课程使用Python或Octave进行有趣的编程，但该课程不教授任何一种语言。
One of the biggest differences with this course is the coverage of the probabilistic approach to machine learning. If you’ve been interested in reading a textbook, like Machine Learning: A Probabilistic Perspective — which is one of the most recommended data science books in Master’s programs — then this course would be a fantastic complement.
本课程最大的区别之一是对机器学习的概率方法的覆盖。 如果您对阅读一本教科书感兴趣，例如《 机器学习：概率论》 (这是硕士课程中最推荐的数据科学书籍之一) ，那么本课程将是一个很好的补充。
Provider: ColumbiaCost: Free to audit, $300 for Certificate
提供者：哥伦比亚费用：免费审核，证书$ 300
Course structure:
课程结构：
- Maximum Likelihood Estimation, Linear Regression, Least Squares 最大似然估计，线性回归，最小二乘
- Ridge Regression, Bias-Variance, Bayes Rule, Maximum a Posteriori Inference 岭回归，偏差方差，贝叶斯规则，最大后验推论
- Nearest Neighbor Classification, Bayes Classifiers, Linear Classifiers, Perceptron 最近邻分类，贝叶斯分类器，线性分类器，感知器
- Logistic Regression, Laplace Approximation, Kernel Methods, Gaussian Processes Logistic回归，Laplace逼近，核方法，高斯过程
- Maximum Margin, Support Vector Machines (SVM), Trees, Random Forests, Boosting 最大保证金，支持向量机(SVM)，树木，随机森林，增强
- Clustering, K-Means, EM Algorithm, Missing Data 聚类，K均值，EM算法，数据丢失
- Mixtures of Gaussians, Matrix Factorization 高斯混合，矩阵分解
- Non-Negative Matrix Factorization, Latent Factor Models, PCA and Variations 非负矩阵分解，潜在因子模型，PCA和变化
- Markov Models, Hidden Markov Models 马尔可夫模型，隐马尔可夫模型
- Continuous State-space Models, Association Analysis 连续状态空间模型，关联分析
- Model Selection, Next Steps 模型选择，后续步骤
Much of the topics in the curriculum are covered in other courses aimed at beginners, but the math isn’t watered down here. If you’ve already learned these techniques, are interested in going deeper into the mathematics, and want to work on programming assignments that actually derive some of the algorithms, then give this course a shot.
该课程中的许多主题都针对其他针对初学者的课程，但此处并未涉及数学。 如果您已经学习了这些技术，并且对深入研究数学感兴趣，并且想要从事实际上派生某些算法的编程工作，那么请尝试一下本课程。
学习指南 (Learning Guide)
Now that you’ve seen the course recommendations, here’s a quick guide for your learning machine learning journey. First, we’ll touch on the prerequisites for most machine learning courses.
现在，您已经看到了课程建议，这是您学习机器学习过程的快速指南。 首先，我们将介绍大多数机器学习课程的先决条件。
课程先决条件 (Course Prerequisites)
More advanced courses will require the following knowledge before starting:
在开始之前，更高级的课程需要具备以下知识：
- Linear Algebra 线性代数
- Probability 可能性
- Calculus 结石
- Programming 程式设计
These are the general components of being able to understand how machine learning works under the hood. Many beginner courses usually ask for at least some programming and familiarity with linear algebra basics, such as vectors, matrices, and their notation.
这些是能够了解机器学习如何在后台进行的一般组件。 许多初学者课程通常要求至少编程和熟悉线性代数基础，例如向量，矩阵及其表示法。
The first course in this list, Machine Learning by Andrew Ng, contains refreshers on most of the math you’ll need, but if you haven’t taken Linear Algebra before, it might be difficult to learn machine learning and Linear Algebra at the same time.
此列表中的第一门课程是Andrew Ng的《 机器学习》 ，其中包含有关您需要的大多数数学的复习课程，但是如果您以前没有学习过线性代数，那么可能很难同时学习机器学习和线性代数时间。
If you need to brush up on the math required, check out:
如果您需要复习所需的数学，请查看：
I’d recommend learning Python since the majority of good ML courses use Python. If you take Andrew Ng’s Machine Learning course, which uses Octave, you should learn Python either during the course or after since you’ll need it eventually. Additionally, another great Python resource is dataquest.io, which has a bunch of free Python lessons in their interactive browser environment.
我建议您学习Python，因为大多数优秀的ML课程都使用Python。 如果您参加了使用Octave的Andrew Ng的机器学习课程，则应该在该课程期间或之后学习Python，因为最终将需要它。 另外，另一个很棒的Python资源是dataquest.io ，在其交互式浏览器环境中有很多免费的Python课程。
After learning the prerequisite essentials, you can start to really understand how the algorithms work.
在学习了必备知识之后，您就可以真正了解算法的工作原理了。
基本算法 (Fundamental Algorithms)
There’s a base set of algorithms in machine learning that everyone should be familiar with and have experience using. These are:
机器学习中有一组基本算法，每个人都应该熟悉并有使用经验。 这些是：
- Linear Regression 线性回归
- Logistic Regression 逻辑回归
- k-Means Clustering k均值聚类
- k-Nearest Neighbors k最近邻居
- Support Vector Machines (SVM) 支持向量机(SVM)
- Decision Trees 决策树
- Random Forests 随机森林
- Naive Bayes 朴素贝叶斯
These are the essentials, but there’s many, many more. The courses listed above contain essentially all of these with some variation. Understanding how these techniques work and when to use them will be extremely important when taking on new projects.
这些是必不可少的，但是还有很多很多。 上面列出的课程基本上包含所有这些内容，但有所不同。 在进行新项目时，了解这些技术的工作原理以及何时使用它们将非常重要。
After the basics, some more advanced techniques to learn would be:
在掌握了基础知识之后，将学习一些更高级的技术：
- Ensembles 合奏
- Boosting 提升
- Dimensionality Reduction 降维
- Reinforcement Learning 强化学习
- Neural Networks and Deep Learning 神经网络与深度学习
This is just a start, but these algorithms are usually what you see in the most interesting machine learning solutions, and they’re effective additions to your toolbox.
这只是一个开始，但是这些算法通常是您在最有趣的机器学习解决方案中看到的，它们是对工具箱的有效补充。
And just like the basic techniques, with each new tool you learn you should make it a habit to apply it to a project immediately to solidify your understanding and have something to go back to when in need of a refresher.
与基本技术一样，您学习的每种新工具都应养成一种习惯，即立即将其应用到项目中，以巩固您的理解，并在需要复习时可以回头。
处理项目 (Tackle a Project)
Learning machine learning online is challenging and extremely rewarding. It’s important to remember that just watching videos and taking quizzes doesn’t mean you’re really learning the material. You’ll learn even more if you have a side project you’re working on that uses different data and has different objectives than the course itself.
在线学习机器学习具有挑战性，并且非常有益。 重要的是要记住，仅观看视频并进行测验并不意味着您真的在学习材料。 如果您正在从事的附带项目使用的数据与课程本身相比具有不同的数据和目标，您将学到更多。
As soon as you start learning the basics, you should look for interesting data to which you can apply those new skills. The courses above will give you some intuition on when to apply certain algorithms, and so it’s a good practice to immediately apply them in a project of your own.
一旦您开始学习基础知识，就应该寻找可以将这些新技能应用到的有趣数据。 上面的课程将为您提供何时应用某些算法的直觉，因此，最好将它们立即应用到您自己的项目中。
Through trial and error, exploration and feedback, you’ll discover how to experiment with different techniques, how to measure results, and how to classify or make predictions. For some inspiration on what kind of ML project to take on, see this list of examples.
通过反复试验，探索和反馈，您将发现如何用不同的技术进行实验，如何测量结果以及如何分类或做出预测。 有关采取哪种ML项目的一些启发，请参阅此示例列表 。
Tackling projects gives you a better high-level understanding of the machine learning landscape, and as you get into more advanced concepts, like Deep Learning, there’s virtually an unlimited number of techniques and methods to understand and work with.
处理项目可以使您对机器学习领域有一个更高层次的理解，并且当您进入更高级的概念(如深度学习)时，几乎可以理解和使用许多技术和方法。
阅读新研究 (Read New Research)
Machine learning is a rapidly developing field where new techniques and applications come out daily. Once you’re passed the fundamentals, you should be equipped to work through some research papers on a topic you’re interested in.
机器学习是一个快速发展的领域，每天都有新技术和应用出现。 一旦掌握了基础知识，就应该具备学习有关感兴趣主题的一些研究论文的能力。
There’s several websites to get notified about new papers matching your criteria. Google Scholar is always a good place to start. Enter keywords like “machine learning” and “twitter”, or whatever else you’re interested in, and hit the little “Create Alert” link on the left to get emails.
有几个网站可让您获得有关符合您条件的新论文的通知。 Google学术搜索始终是一个不错的起点。 输入诸如“机器学习”和“推特”之类的关键字，或者您感兴趣的其他任何内容，然后点击左侧的小“创建警报”链接以获取电子邮件。
Make it a weekly habit to read those alerts, scan through papers to see if their worth reading, and then commit to understanding what’s going on. If it has to do with a project you’re working on, see if you can apply the techniques to your own problem.
养成每周阅读这些警报，浏览论文以查看其是否值得阅读的习惯，然后致力于理解正在发生的事情。 如果与您正在从事的项目有关，请查看是否可以将技术应用于您自己的问题。
结语 (Wrapping Up)
Machine learning is incredibly fun and interesting to learn and experiment with, and I hope you found a course above that fits your own journey into this exciting field.
机器学习是非常有趣和有趣的学习和实验，我希望您能找到一个适合您自己进入这个令人兴奋领域的课程。
Machine learning makes up one component of Data Science, and if you’re also interested in learning about statistics, visualization, data analysis, and more, be sure to check out the top data science courses, which is a guide that follow a similar format to this one.
机器学习是数据科学的一个组成部分，如果您还对学习统计数据，可视化，数据分析等感兴趣，请务必阅读热门的数据科学课程 ，这是遵循类似格式的指南到这个。
Lastly, if you have any questions or suggestions, feel free to leave them in the comments below.
最后，如果您有任何问题或建议，请随时在下面的评论中保留。
Thanks for reading and have fun learning!
感谢您的阅读，并祝您学习愉快！
Originally published at learndatasci.com.
最初发布于learningdatasci.com 。
翻译自: https://www.freecodecamp.org/news/top-5-machine-learning-courses-for-2019-8a259572686e/
2019机器学习比赛
3011
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
