This training provides a theoretical introduction into the basics of Machine Learning and its different sub-fields, as well as a hands-on way of seeing how it is applied in practice. At the core of this training is the scikit-learn library, one of the most powerful and versatile tools for Machine Learning in Python.

The training includes theory, demos, and hands-on exercises.

After this training you will have gained knowledge about:

• Machine Learning, its goals and potential applications
• Different types of Machine Learning: supervised, unsupervised and reinforcement learning
• Classification and regression problems
• Techniques such as clustering and dimensionality reduction
• A minimal example workflow of a prediction model in scikit-learn
• Splitting datasets into training and test sets
• How to train, predict, and score a classification prediction model
• The standard interfaces of scikit-learn classes
• Transformers and estimators in scikit-learn
• Some of the machine learning algorithms you’ll have at your disposal, such as k-nearest neighbors, logistic regression, support vector machines, neural networks, etc.

In the second training, we build upon what we have learned previously, and expand our workflow by showing how to optimize prediction models using Parameter Tuning. We discuss how and why to perform Cross-Validation and how to prevent Information Leakage. Bringing everything together, we finally show how to combine multiple steps of a machine learning workflow into pipelines, thereby making the process more organized, efficient and less error-prone.

The training includes theory, demos, and hands-on exercises.

After this training you will have gained knowledge about:

• Cross-Validation
• Commonly used Cross-Validation strategies
• The importance of a validation set
• Information leakage
• Workflow of grid search and cross validation
• Standard interfaces of the GridSearchCV class
• Pipelines and their role in combining transformers and estimators

In the last training of the series, we expand our knowledge of how to score machine learning models, discuss common pitfalls and show how to deal with them. We will do this by first examining the concepts of bias, variance, overfitting and underfitting, followed by diving into important performance metrics such as accuracy, precision, recall, F1 scores, ROC curves, etc. for classification problems and elaborating on commonly used metrics for regression. This last part in our basic toolkit allows us to properly assess a prediction model that we train to recognize images of handwritten digits during the hands-on lab session.

The training includes theory, demos, and hands-on exercises.

After this training you will have gained knowledge about:

• Overfitting, underfitting. bias-variance tradeoff
• Model evaluation in practice using sci-kit learn
• Evaluation metrics for classification, such as accuracy, precision, recall, F1, area under curve
• Interpreting confusion matrices, classification reports and ROC curves
• Decision function and classification probabilities
• Dealing with unbalanced datasets
• Evaluation metrics for regression, such as MAE, RMSE, R^2