- (incorporates former Speagram)
Artificial General Intelligence
Algorithmic Game Theory: Prediction Markets (po polsku)
Programming in Java
kurs pracy w systemie Linux
Data Stores and Data Mining
Systemy Inteligentnych Agentów
Przetwarzanie Języka Naturalnego
Overall course focus: (hmm…)
- Reinforcement learning.
- Concept formation and program synthesis.
- Adaptive and probabilistic logics.
- Mental development theory.
- Universal Artificial Intelligence: universal induction, exhaustive program search and reinforcement learning algorithms Δ (TeXmacs source Δ)
- Techniques of Reinforcement Learning Δ (TeXmacs source Δ)
- RL_Ch6_Evolutionary_modular.pdf Δ
- RL_Ch7_Hierarchical_RL.pdf Δ
- General Game Playing Δ (TeXmacs source Δ)
- Knowledge Representation and Language Δ (TeXmacs source Δ)
- Adaptive and Probabilistic Logics for Reasoning Systems
- Adaptive (or Defeasible) Logics and OSCAR Δ (TODO: complete the notes about OSCAR)
- Frequency and/or Uncertainty Logics: Non Axiomatic Logic, Markov Logic Networks Δ, Probabilistic Logic Networks (to come)
- I’ve presented OSCAR and comments on John Pollock’s theory supported by his slides and article figures, I also introduced “propositional” NARS
- Estimation of Distribution Algorithms and Genetic Programming Δ (TeXmacs source Δ)
- Inductive (Logic) Programming
- Spreading Activation: memory retrieval, distributed reasoning, action selection, probabilities Δ (work in progress) approaches based on spreading activation mechanism or strong biological inspirations
- The Representation and Acquisition of Concepts Δ (to come later)
- Cognitive Architectures
I’ve moved KR before logics to introduce representation means of representation-specific reasoning systems (NARS and PLN) there.
- Values and Others: Grounding Agents in Game Semantics Δ (to come)
- We build semantics in both representational and logic aspects based on the notion of agent specific rewards/motivations.
Artificial General Intelligence: A Gentle Introduction by Pei Wang
Major online reading:
More online reading:
Major offline reading (available to me):
- “Artificial General Intelligence”, Ben Goertzel, Cassion Pennachin (editors), 2007, Cognitive Technologies series at Springer
- “Rigid Flexibility. The Logic of Intelligence”, Pei Wang, 2006, Applied Logic series at Springer
- “Universal Artificial Intelligence. Sequential Decisions based on Algorithmic Probability”, Marcus Hutter, 2005, Texts in Theoretical Computer Science series at Springer
- “Knowledge Representation and the Semantics of Natural Language”, Hermann Helbig, 2006, Cognitive Technologies series at Springer
- “The Cambridge Handbook of Thinking and Reasoning”, Keith Holyoak, Robert Morrison (editors), Cambridge University Press, 2005
Architectures / projects:
Some video lectures (currently not well selected):
- Information, distributions, programs, intelligence.
- Shannon information and Kolmogorov information, measures of complexity.
- Decision and control theory topics. Markov decision processes, reinforcement learning (Q-learning, SARSA etc.).
- SAIL and Dav: robots that learn “from scratch”.
- “General algorithmic intelligence” AIXI.
- Self improving programs: “Goedel Machine”. “Verificationist” program synthesis.
- Graphical probability models.
- Bayesian networks.
- Hierarchical Temporal Memory from Numenta.
- Introduction to “estimation of distribution” algorithms.
- “Optimizationist” competent program synthesis: algorithm MOSES.
- Representing and learning concepts. PAC-learnability.
- Learning grammars.
- Higher order and recursive structure representation induction.
- Logic in a dynamic world.
- Adaptive logics overview (circumscription, defeasible argumentation, belief revision, etc.) Intensional and term logics.
- From semantic networks to logic: system SNePS.
- Reasoning about probability and uncertainty.
- Game semantics for logics.
- Recursive probability models.
- Probabilistic term logic. “Two-dimensional” truth values: system NARS.
- “Probabilistic Logic Networks” in Novamente.
- Inductive probabilistic logic programming vel probabilistic logic learning.
- Cognitive loop (in search for the “main()” of the artificial mind).
- Inference system as an agent: goals and activations. (SNePS, NARS)
- Cognitive loop in LIDA.
- Concept formation and modeling of self. (Novamente)
- Theory of mental development.
- Piagetan psychology.
- Mental development of an AGI.