Best Machine Learning Classes Online

Offered through University of California San Diego Extension, this course prepares advanced programmers for careers in machine learning. Students start with learning about and analyzing data, before moving into machine learning algorithms and deep learning. Students gain hands-on experience developing machine learning platforms and have the option of specializing in advanced deep learning, image processing, or natural language processing with additional study. Career coaching is integrated into the course curriculum, and students produce a machine learning capstone project for their professional portfolio.

For students pursuing a careers as a Microsoft Certified Azure Data Scientist Associate, this course helps prepare for the exam. The course covers subjects on the exam such as data processing and statistical analysis as well as principle component analysis and logistic and linear regression. Students also gain experience with decision trees and hyperparameter tuning as well as cluster analysis and K-means clustering. At the end of the course, students earn a certificate of completion.

In this course, students interested in learning about machine learning gain hands-on experience. Working with Python, students learn about regression, clustering, Bayesian methods and decision trees, and support vector machines. The course also covers reinforcement learning and collaborative filtering as well as ensemble learning, frequency, experimental design, and A/B testing. By the end of the course, students will be able to tackle the final project, and also understand how to scale up machine learning with Apache Spark.

This substantial ten-part course introduces students to the area of machine learning in data science. Students start by learning essential skills with Python and R then work with regressions, classifications, and clustering. Then, students learn algorithms and start using them to solve problems before discovering Natural Language Processing, deep learning, and gradient boosting. By the end of the course, students will have worked on multiple hands-on exercises for cementing their new knowledge of machine learning.

Designed for students who have skills with Python and probability, this machine learning course focuses exclusively on leveraging Bayesian machine learning for A/B testing. Students develop familiarity with the explore-exploit dilemma and the Epsilon-Greedy algorithm. The course also guides students through the UCB1 algorithm. Practical activities allow students to gain hands-on experience with the Bayesian method before they earn their certificate of completion.

For students interested in machine learning, this very short course introduces the essentials of the field. Students learn about supervised and unsupervised learning while acquiring the vocabulary of machine learning. Then, students learn to write classifiers and make predictions in Scikit-learn. For peer learning support, students can tap into the Treehouse learning community.

This tutorial introduces students to machine learning and artificial intelligence. The class demonstrates machine learning models and helps students build their own face emotion classifier. Students also gain practice in finding machine learning problems in AI products. By the end of the class, students will be familiar with major concepts including regression, classification, and featurization.

Students curious about artificial intelligence can take this tutorial to learn about its relationship to machine learning. The course discusses machine learning as a field as well as its features, tools, and applications. Students learn how to use machine learning in their own lives and work and how audio and video figure into machine learning. By the end of the course, students will also understand the ethics of AI and machine learning.

Machine learning students familiar with scikit-learn can study this course to advance their skills with tree-based models. The course begins with an orientation to Classification and Regression Trees and their algorithm. Then, students learn about bias-variance tradeoff, overfitting and underfitting, ensembling, bagging, and the random forest algorithm. Finally, the course covers boosting with AdaBoost and Gradient Boosting and model tuning with grid search cross validation.

Students with experience in scikit-learn can expand their machine learning skillset with this short course on TensorFlow. The course begins with an orientation to TensorFlow, demonstrating the use of constants, variables, and derivatives. Then, students build linear models, gaining experience with loss functions, linear regression, and batch training before then using those skills to build a neural network. The last unit covers working with Keras and Estimators APIs.

In this short course, deep learning students learn essential skills with Keras to process images with machine learning. Students discover convolutional neural networks and train a model for recognizing objects in images, then explore further how to create and use convolutions in Keras neural networks. The course also covers building deep learning networks and working with parameters and pooling operations. The last unit helps students track results and tweak their neural networks.

Designed for machine learning beginners, this short course introduces sudents to supervised learning. The course begins with an introduction to the k-Nearest Neighbors algorithm before demonstrating Bayesian methods with Naive Bayes. Then, students practice with logistic regression, working with ROC curves, AUC, and stepwise regression. Finally, the course introduces students to classification trees and random forest models.