A cognitive model is a descriptive account or computational representation of human thinking about a given concept, skill, or domain. A cognitive model of learning, includes both a way of organizing knowledge within a subject area and an account of how humans develop accurate and complete knowledge of that subject area. Learning designers engage in a variety of practices to unpack knowledge from subject matter experts and novices to develop cognitive models of learning and use those models to guide the design of instruction or instructional technologies. Traditional approaches to eliciting and organizing knowledge, such as conducting a cognitive task analysis (CTA)  with experts and novices, are labor-intensive and require specific expertise that many learning designers do not have. However, learning data generated from learners’ interaction with courses, can provide insight into how humans think and develop knowledge. As a continued effort, we extend the framework presented in our earlier work  to discover and refine cognitive models of learning with learning data. The framework includes 1. a Variational Autoencoder (VAE) and a Gaussian Mixture Model (GMM) that models and clusters cognitive learning patterns; 2. a multidimensional measure that quantifies validity and reliability of the discovered cognitive models of learning; 3. a topic-based solution that interprets the cognitive models from a linguistic perspective; and 4. a simulation-based analysis for both accuracy measures and course refinement insights. We demonstrate the end-to-end solution with two applications and four case studies that are deployed in an openly navigated learning system in a workforce learning environment. We also report the usefulness of the discovered cognitive models of learning with subject matter expert evaluation.