Learn to train and assess models performing common machine learning tasks such as classification and clustering.

Start Course for Free6 Hours15 Videos81 Exercises93,996 Learners

6500 XPor

By continuing, you accept our Terms of Use, our Privacy Policy and that your data is stored in the USA. You confirm you are at least 16 years old (13 if you are an authorized Classrooms user).This online machine learning course is perfect for those who have a solid basis in R and statistics, but are complete beginners with machine learning. After a broad overview of the discipline's most common techniques and applications, you'll gain more insight into the assessment and training of different machine learning models. The rest of the course is dedicated to a first reconnaissance with three of the most basic machine learning tasks: classification, regression and clustering.

- 1
### What is Machine Learning

**Free**In this first chapter, you get your first intro to machine learning. After learning the true fundamentals of machine learning, you'll experiment with the techniques that are explained in more detail in future chapters.

Machine Learning: What's the challenge?50 xpAcquainting yourself with the data100 xpWhat is, what isn't?50 xpWhat is, what isn't? (2)50 xpBasic prediction model100 xpClassification, Regression, Clustering50 xpClassification, regression or clustering?50 xpClassification: Filtering spam100 xpRegression: LinkedIn views for the next 3 days100 xpClustering: Separating the iris species100 xpSupervised vs. Unsupervised50 xpGetting practical with supervised learning100 xpHow to do unsupervised learning (1)100 xpHow to do unsupervised learning (2)100 xpTell the difference50 xp - 2
### Performance measures

You'll learn how to assess the performance of both supervised and unsupervised learning algorithms. Next, you'll learn why and how you should split your data in a training set and a test set. Finally, the concepts of bias and variance are explained.

Measuring model performance or error50 xpThe Confusion Matrix100 xpDeriving ratios from the Confusion Matrix100 xpThe quality of a regression100 xpAdding complexity to increase quality100 xpLet's do some clustering!100 xpWhat to do with all these performance measures?50 xpTraining set and test set50 xpSplit the sets100 xpFirst you train, then you test100 xpUsing Cross Validation100 xpHow many folds?50 xpBias and Variance50 xpOverfitting the spam!100 xpIncreasing the bias100 xpInterpretability50 xp - 3
### Classification

You'll gradually take your first steps to correctly perform classification, one of the most important tasks in machine learning today. By the end of this chapter, you'll be able to learn and build a decision tree and to classify unseen observations with k-Nearest Neighbors.

Decision trees50 xpLearn a decision tree100 xpUnderstanding the tree plot50 xpClassify with the decision tree100 xpPruning the tree100 xpInterpreting the tree50 xpSplitting criterion100 xpk-Nearest Neighbors50 xpPreprocess the data100 xpThe knn() function100 xpK's choice100 xpInterpreting a Voronoi diagram50 xpThe ROC curve50 xpCreating the ROC curve (1)100 xpCreating the ROC curve (2)100 xpThe area under the curve100 xpInterpreting the curves50 xpComparing the methods100 xp - 4
### Regression

Although a traditional subject in classical statistics, you can also consider regression from a machine learning point of view. You'll learn more about the predictive capabilities and performance of regression algorithms. At the end of this chapter you'll be acquainted with simple linear regression, multi-linear regression and k-Nearest Neighbors regression.

Regression: simple and linear!50 xpSimple linear regression: your first step!100 xpPerformance measure: RMSE100 xpPerformance measures: R-squared100 xpAnother take at regression: be critical100 xpNon-linear, but still linear?100 xpInterpreting R-squared50 xpMultivariable Linear Regression50 xpGoing all-in with predictors!100 xpAre all predictors relevant?100 xpAre all predictors relevant? Take 2!100 xpInterpreting the residuals and p-values50 xpk-Nearest Neighbors and Generalization50 xpDoes your model generalize?100 xpYour own k-NN algorithm!100 xpParametric vs non-parametric!100 xp - 5
### Clustering

As an unsupervised learning technique, clustering requires a different approach than the ones you have seen in the previous chapters. How can you cluster? When is a clustering any good? All these questions will be answered; you'll also learn about k-means clustering and hierarchical clustering along the way. At the end of this chapter and our machine learning video tutorials, you’ll have a basic understanding of all the main principles.

Clustering with k-means50 xpk-means: how well did you do earlier?100 xpThe influence of starting centroids100 xpMaking a scree plot!100 xpWhat is your optimal k?50 xpPerformance and scaling issues50 xpWhen to standardize your data?50 xpStandardized vs non-standardized clustering (1)100 xpStandardized vs non-standardized clustering (2)100 xpHierarchical Clustering50 xpDid you get it all?50 xpSingle Hierarchical Clustering100 xpComplete Hierarchical Clustering100 xpHierarchical vs k-means100 xpInterpreting Dunn's Index50 xpClustering US states based on criminal activity100 xp

Datasets

CarsEmailsTitanicAirSeedsIncomeKangoroosWorld Bank dataSchool resultsOlympic run recordsCrime dataCollaborators

Filip SchouwenaarsDoctoral Student at Vrije Universiteit Brussel

Even though Gilles has recently graduated with a degree in Fundamental Mathematics, he knows that there's more to be done than mathematics. With a solid knowledge in classical statistics, he now pursues a PhD in parallelizing regression modeling techniques.

Data Science Instructor at DataCamp

Vincent has a Master's degree in Artificial Intelligence, and has more than 3 years of experience with machine learning problems of different kinds. He experienced first-hand the difficulties that come with building and assessing machine learning systems. This made him passionate about teaching people how to do machine learning the right way.

“I've used other sites—Coursera, Udacity, things like that—but DataCamp's been the one that I've stuck with.”

Devon Edwards Joseph

Lloyds Banking Group

“DataCamp is the top resource I recommend for learning data science.”

Louis Maiden

Harvard Business School

“DataCamp is by far my favorite website to learn from.”

Ronald Bowers

Decision Science Analytics, USAA

or

By continuing, you accept our Terms of Use, our Privacy Policy and that your data is stored in the USA. You confirm you are at least 16 years old (13 if you are an authorized Classrooms user).