Path Category
Loading Path Category from the AllPath API…
ALLPATHFoundationALLPATHFoundationPath Category
Loading Path Category from the AllPath API…
Path Category
Guided learning journeys that build knowledge step by step.
category · Learning · slug · learning · 7812 Paths
7812 Paths · page 392 / 782
This learning path introduces the core concepts of neural networks, from the perceptron to multi-layer networks trained with backpropagation. It builds on foundational calculus and linear algebra, ensuring learners understand both the intuition and the mathematics behind each component.
This path covers the core concepts and techniques of unsupervised learning, including clustering (K-means, hierarchical), dimensionality reduction (PCA, t-SNE), and anomaly detection. It starts with essential prerequisites in linear algebra and machine learning fundamentals, then builds up to practical applications.
This path guides AI/ML students from foundational calculus and ML principles through core supervised learning algorithms, including linear and logistic regression, k-NN, decision trees, and SVMs, culminating in model evaluation. It emphasizes conceptual understanding and practical application.
A structured path for CS students to understand core machine learning concepts, covering supervised, unsupervised, and reinforcement learning, along with essential practices like train/test splits and overfitting. It builds on programming and probability fundamentals, progressing from basic definitions to intermediate analysis techniques such as bias-variance tradeoff.
This learning path introduces high school students to probabilistic reasoning in artificial intelligence. It covers basic probability concepts, Bayesian networks, inference techniques, and decision theory, enabling learners to understand and apply probabilistic models in AI contexts.
This learning path introduces the fundamentals of logic-based knowledge representation and inference in artificial intelligence. Starting with propositional logic, it progresses through inference rules, forward and backward chaining, and resolution, and culminates in first-order logic inference. Designed for high school students with no prior logic background.
This learning path introduces high school students to the core formalisms AI systems use to represent knowledge. It begins with the foundations of logic, moves through propositional and first-order logic, and then explores structured representations such as semantic nets and frames, culminating in production rules. The path emphasizes how each scheme captures knowledge for reasoning and problem-solving.
This learning path introduces fundamental search algorithms used in artificial intelligence for problem-solving. Starting with problem formulation and basic data structures, it covers uninformed searches (BFS, DFS) and informed searches (Greedy, A*) with heuristics. By the end, learners will be able to formulate problems as search problems and compare different search strategies.
This learning path introduces high school students to the field of Artificial Intelligence, covering its definition, history, core concepts, types, and real-world applications. It also includes essential basics in programming and mathematics to provide a solid foundation for understanding AI.
This learning path guides aspiring HCI researchers through the complete research process, from understanding the field and conducting literature reviews to designing and executing studies, analyzing data, and writing and presenting results. It emphasizes rigorous methodology, ethical practice, and reproducibility, preparing learners to contribute original research to venues like CHI.