AI curriculum
Course outline for Neuro-Symbolic AI
Generated suggestions may violate explicit domain rules. Combine model outputs with symbolic representations and constraint checks for inspectable hybrid reasoning.
About Neuro-Symbolic AI
Generated suggestions may violate explicit domain rules. Combine model outputs with symbolic representations and constraint checks for inspectable hybrid reasoning.
Neuro-Symbolic AI Course Objectives
- Compare neural and symbolic reasoning roles.
- Represent rules and relationships for a small domain.
- Validate generated suggestions against explicit constraints.
Pre-requisites
- Familiarity with language models and knowledge representation.
- Basic programming and logical reasoning skills.
Lab Setup
- Computer with a programming runtime and a local rule or graph library.
- Use a local model or supplied suggestions and synthetic domain facts.
Detailed Course Outline
Proposed modulesModule 1: Complementary representations
- Symbolic AI
- Neural AI
- Rule-based reasoning
- Knowledge graphs
Practical outcome: Separate learned suggestions from explicit domain rules.
Module 2: Hybrid validation
- Ontologies
- LLM + symbolic systems
- Constraint checking
- Hybrid reasoning
Practical outcome: Reject or revise suggestions that violate a constraint.
Practical exercise
- Prototype a hybrid decision pipeline and explain its rule checks and unresolved uncertainty.
How we train
Contact us for full course details, including duration, delivery options and lab requirements.
Ask about exercises, instructor feedback and the prior knowledge you need. Tool-specific courses marked provisional may become modules in a broader course.
Discuss your learning goals