AI Skills: Basic and Advanced Techniques in Machine Learning

This series of hands-on and interactive MOOCs will give learners a comprehensive overview of the basics machine learning topics. You will discover how machine learning classification and regression techniques allow you to make predictions for a category (classification) or for a number (regression) given data. This can be useful in predicting properties of objects (such as their weight or shape), or predicting qualities of people (customer satisfaction, etc.). You will learn about unsupervised learning techniques such as clustering and dimensionality reduction and how useful they are to make sense of large and/or high dimensional datasets. We will also cover more advanced supervised learning techniques such as deep learning. This is useful to train neural networks to solve more complicated classification and regression tasks. Finally, you will deep dive into the reinforcement learning techniques and understand how to use them to train AI agents that interact with an environment. The lectures feature a unique combination of videos mixed with hands-on interaction with machine learning algorithms to stimulate a deeper understanding. In the exercises you apply the algorithms in Python using scikit-learn and in the final project you will further deepen your understanding of the various concepts by building and tuning a machine learning pipeline from start to finish.

Apply common operations (pre-processing, plotting, etc.) to datasets using Python. Explain the concept of supervised, semi-supervised, unsupervised machine learning and reinforcement learning. Explain how various supervised learning models work and recognize their limitations. Analyze which factors impact the performance of learning algorithms. Apply learning algorithms to datasets using Python and Scikit-learn and evaluate their performance. Optimize a machine learning pipeline using Python and Scikit-learn. Describe the main classes of clustering techniques. Implement k-means and hierarchical clustering. Motivate the need and choice of dimensionality reduction techniques. Implement Principal Component Analysis (PCA) for feature extraction. Explain how deep neural networks work and their advantages. Train deep neural networks for classification and regression tasks. Explain the basic concepts and techniques of reinforcement learning. Describe how reinforcement learning could be applied in real world applications.

See coursepages

The courses in this program are MOOCs that can be followed for free. In order to earn a certificate a fee is required. AI Skills for Engineers: Supervised Machine Learning AI Skills: Introduction to Unsupervised, Deep and Reinforcement Learning

At the beginning of each course, you will have access to the assessment methods and criteria. Most of the assignments are completed throughout the course, but in some cases you might need to do a proctored exam at the end.