Open Learning Paths
Community-curated knowledge paths through the knowledge graph. Open, transparent, and verifiable.
Available Paths
Community-maintained knowledge paths. Each path is defined as a sequence through the knowledge graph with defined prerequisites and dependencies.
Introduction to Computer Science
A foundational path covering the core concepts of computer science, from algorithms and data structures to computer architecture and the theory of computation. Designed for learners with basic mathematical knowledge.
Mathematics for Machine Learning
Covers the essential mathematical foundations required for understanding machine learning: linear algebra, multivariate calculus, probability theory, and optimization methods. Prerequisite knowledge is high-school level mathematics.
Data Structures and Algorithms
A systematic study of fundamental data structures (arrays, linked lists, trees, graphs, hash tables) and algorithms (sorting, searching, graph traversal, dynamic programming). Includes complexity analysis and practical implementation guidance.
Natural Language Processing Fundamentals
An introduction to computational linguistics and NLP, covering tokenization, parsing, semantic analysis, word embeddings, and modern transformer architectures. Builds on foundations in probability and linear algebra.
Knowledge Graph Engineering
Covers the theory and practice of building knowledge graphs: ontology design, entity resolution, relation extraction, graph databases, and reasoning systems. Includes case studies from Wikidata and the Semantic Web.
Path Creation
Learning paths are created through a transparent community process. Every step is documented and publicly visible.