Introduction to basic statistical modeling using R, focusing on simple linear regression analysis. Students will learn to fit regression models between two variables, interpret R output, make predictions using models, and validate model assumptions.

Advanced regression modeling techniques, expanding from simple to multiple linear regression. Students learn to work with both continuous and categorical variables, adapt regression models for complex scenarios, and select optimal models based on R output analysis.

Focus on handling complex data structures in R, particularly nested dataframes. Students learn to apply simultaneous linear models to large data frames through data stratification and interpret the results of learner models.

Introduction to categorical response modeling, covering various classification techniques. Students learn to implement and understand Logistic Regression, Generalized Linear Models (GLMs), and Linear Discriminant Analysis (LDA) in R.

Comprehensive exploration of predictive modeling techniques, focusing on model building and evaluation. Topics include data splitting, cross-validation, model selection, and analysis of overfitting and bias-variance trade-offs in prediction problems.

Introduction to distributed computing with Apache Spark through sparklyr. Students learn to set up and apply sparklyr, and use logical verbs in R by implementing native sparklyr versions of the verbs.

Application of sparklyr to machine learning tasks, focusing on regression and classification models. Students learn to implement machine learning models for prediction and use distributed computing techniques for large-scale problems.

Introduction to deep learning concepts and techniques. Students learn to train multi-layer networks for classification, understand key principles of network training, and use sparklyr and H2O for implementing deep networks.

Advanced deep learning applications focusing on working with massive unlabeled and partially labeled datasets. Students learn to leverage pre-trained networks and implement architectures for object classification and detection.

A synthesis module that consolidates understanding of all methodologies covered in the course. Students learn to evaluate the relationships between different methods and assess their relative strengths, weaknesses, and applications.