Knowledge representation

Mohamed Moalin
Mind Map by Mohamed Moalin, updated more than 1 year ago
Mohamed Moalin
Created by Mohamed Moalin over 6 years ago



Resource summary

Knowledge representation
  1. Human brain - Long-term memory analogy
    1. Declarative Memory
      1. Associated with knowing "what things are" i.e., facts
      2. Procedural Memory
        1. Associated with knowing "how to do things" i.e., Methods
      3. Implicit Knowledge
        1. Neural networks
          1. Used in powerful pattern matchers
            1. Agent trains and learns in new situations
              1. Sensitive to training set
                1. Implicit formation of knowledge by activation
              2. Behavioural based
                1. Rodney Brooks
                  1. Post-experience planning
                  2. Emergent behaviour
                    1. Simple agents produce a non-explicitly programmed complex behaviour
                      1. Analogies
                        1. Birds swarming
                          1. Ants co-operating
                      2. Chunking
                        1. Problem decomposition
                          1. Solve & cache solutions to sub-problems
                            1. Combine cached solutions forming one solution
                      3. Explicit Knowledge
                        1. GOFAI
                          1. Knowledge of World
                            1. Observed, acquired, interrogated & revealed
                              1. Engineered, reasoned, used & deducted
                                1. Hierarchical planning
                                  1. Meta-level: scheduling, planning, ordering
                                2. Lacks & constraints
                                  1. Reactive planning & problem solving
                                    1. Environmental needs
                                      1. Maximum observability
                                        1. All aspects relevant to choice of action observable
                                        2. Deterministic environment
                                          1. Saves worrying about uncertainty
                                          2. Static environment
                                            1. Environment doesn't change whilst agent delibrates
                                          3. Adaptability
                                        3. Facts & Rules
                                          1. Data Structures
                                            1. Semantic nets
                                              1. Symbolic representation of relationships between concepts
                                              2. Frames
                                                1. Hierarchical structure
                                                  1. Classes, sub-classes
                                                    1. Instances (e.g., name)
                                                      1. Slot:fillers(i.e., description of attributes)
                                                Show full summary Hide full summary


                                                d _ b
                                                Propositional Calculus
                                                Mohamed Moalin
                                                Artifical Intellegence Final
                                                Thomas Scott
                                                Inteligencia Artificial
                                                Jean Ramírez
                                                Emerging AI apps that are trying to make us better parents
                                                Ramadhani Hayeshi
                                                Qidiruv orqali masalalarni yechish. Amaliy
                                                Fazil Zaripov
                                                Unfinished NN types
                                                Max The Mooshroom
                                                Neural networks
                                                Alexander Kozlovsky