Post on 25-Dec-2015
Novamente:An Integrative Approach to Embodied Artificial General Intelligence
Ben Goertzel
Novamente LLC
Overview
Artificial General IntelligenceHistorical Approaches to AIThe Importance of EmbodimentStages of Cognitive DevelopmentThe AGI-SIM Simulation WorldThe Novamente AI ArchitectureLearning to Play Fetch and TagObject Permanence and Word-Object AssociationSteps Toward Human-Level AI
Artificial General Intelligence (AGI)
“The ability to achieve complex goals in complex environments using limited computational resources”
• Autonomy• Practical understanding of self and others• Understanding “what the problem is” as opposed to
just solving problems posed explicitly by programmers
Existing AI Paradigms
Paradigm Strengths Weaknesses
GOFAI Representation of abstract knowledge
Reasoning (short proofs)
Pattern recognition
Learning
Autonomy
Neural nets Pattern recognition
Learning
Associative memory
Perception/action/cognition integration
Representation of abstract knowledge
Abstract reasoning
Learning
Autonomy
Evolutionary Programming
Pattern recognition
Learning of complex procedures
Representation of abstract knowledge
Abstract reasoning
Autonomy
Probabilistic Reasoning
Representation of abstract uncertain knowledge
Reasoning (short proofs)
Hypothesis formation
Autonomy
Pattern recognition
Subsumption Robotics
Autonomy
Learning
Perception-action integration
Cognition
Representation of abstract knowledge
Embodiment (real or virtual) provides a would-be AGI with
Symbol grounding Most crucially: grounding of subtle words like prepositions
An effective medium for learning complex cognitive skills attention allocation procedure-learning inference control
A sense of self Critical for cognition as well as mental health
Empathy with humans
The Power of Embodiment
Stages of Cognitive Development
Infantile
• Instinct
• Imitation
• Word-Object Association
• Object Permanence
Pre-Operational
• Simple syntax
• Systematic word-object associations
• Single-parameter object classifications
Concrete Operational
• Conservation Laws
• Theory of Mind
• Complex object classifications
• Advanced syntax
Formal
• Abstract deductive reasoning
• Scientific testing of hypotheses
(a path toward embodied AGI, inspired by the classic work of Jean Piaget)
AGI-SIM: An Open-Source Simulation
Environment for AGI
AI systems can sense and act in real-time via embodiment in a 3D virtual worldUses CrystalSpace (open-source game engine) for visualization Provides AI systems with multisensory inputs visual inputs at varying levels of granularity:
pixels, polygons or objects hearing, touch, proprioception, …
Integration with natural language interface for fluid, situated communicationSuitable for teaching/learning based on a developmental-psychology-based methodologyCompatible with Novamente but usable by any AI system via a simple sockets-based protocol
AGI-SIM Status
Version 1 complete and usable Available on SourceForge
Work in progress: More complete set of wireframe models Multi-room simulated world Realistic physics
Via integration of Open Dynamics Engine Integration of NLP chat
AI systems may viably synthesize knowledge gained via various means
virtually embodied experience AGI-SIM
physically embodied experience robotics
explicit encoding of knowledge in natural language ingestion of databases quantitative and relational
Post-Embodied AI
The Novamente Project
Long-term goal: creating "artificial general intelligence" approaching and then exceeding the
human level to be approached via a series of incremental phases
Novamente AI Engine: an integrative AI architecture synthesizes ideas from cognitive and neural science with computer science
algorithms such as evolutionary programming and probabilistic inference uses a unique "weighted labeled hypergraph" knowledge representation Efficient, scalable C++/Linux implementation
Currently parts of the Novamente codebase are being used for commercial projects
natural language processing biological data analysis
The Novamente Project
Moving Toward General Intelligence
Novamente is being used to control an embodied virtual agent in a 3D simulation world called AGI-SIM.
A loosely-Piaget-inspired series of cognitive developmental stages is being used to guide the process of teaching Novamente to carry out a series of progressively more complex tasks in the AGI-SIM environment.
The same approach being used within AGI-SIM may be used in future to embody Novamente in physical robots, including humanoid robots or automated vehicles.
Key Conceptual Aspects of Novamente
Knowledge representation is transparent wherever possible
Procedural and declarative knowledge are easily interconvertible
Evolutionary learning is used to supply creativity for both procedural and declarative knowledge
Probabilistic logical inference is used for basic reinforcement learning as well as abstract thinking
Architecture supports interaction of multiple specialized agents acting on a common knowledge store, along with processes of truly general scope
Design covers all aspects of human and machine cognition
Key Novamente Design Aspects
Aspect Function
Node Denotes a percept, set, list or action
Link Denotes a logical, associative or action relationship
MindAgent A persistently active cognitive, perceptual or active process
Core The “Mind OS” that maintains the store of nodes/links and executes MindAgents and Tasks
Map A semantically significant pattern of activation of MindAgents, Nodes and Links
Unit A collection of nodes, links and MindAgents grouped together to carry out some particular function (like perception, language processing, or abstract reasoning)
NovamenteNode and Links
Node types: WordNode, NumberNode, CharacterNode,… ConceptNode, ProcedureNode, PredicateNode,…
Link types: SimilarityLink, InheritanceLink, ImplicationLink,
EquivalenceLink,… ProcedureApplicationLink, PredicateEvaluationLink,…
Nodes and links weighted with: Probabilistic truth values Attention values similar to neural network activations
Architecture of a Novamente Lobe
MindAgents are based on
•Probabilistic Term Logic
•BOA-based Evolutionary Procedure Learning
•Frequent Itemset Mining
•Stochastic Local Search
Example MindAgents:
•First-order probabilistic inference
•Schema Learning with BOAP
•Probabilistic Attention Allocation
•Procedure and Predicate Evaluation
•Sentence Parsing
•Word Sense Disambiguation
•Sentence Production
•…
Distributed Novamente Architecture
Novamente Architecture:High-Level View
Learning to Play Fetch
ifelse holding(ifelse facingteachersteprotate)(ifelse nearballpickup(ifelse facingballstep
rotate))
Example program for learning to fetch a ball and bring it to the teacher, learned using Novamente’s BOA procedure learning algorithm
Learned via giving Novamente partial reinforcement for bringing the ball near the teacher
Learning to Play Fetch
Interpretation of Example Program
If holding the ball and facing the teacher move forward (to give the ball to the teacher)
Otherwise, if holding the ball, rotate ( in order to face the teacher)
Otherwise, if near the ball, pick it up
Otherwise, if facing the ball, move forward (to get the ball)
Otherwise, rotate (in order to face the ball)
Learning to Play Tag
Agents controlled by BOA learn rules for playing “tag” via reinforcement learning in a tag tournamentOptimal rules learned depend on ratio between agents’ speed and step sizeAn example of “cooperative learning” among a community of agents
Step size significantly smaller than robot diameter
(ifelse it
opponentangle
- opponentangle 3.1416)
step
Step size equal to robot diameter
(ifelse it
opponentangle
- opponentangle 1.5708)
step
Learning to Play Tag
Not-IT’s
Great Escape
Next Steps
Fall 2005 Milestones:
Oct. -- Complete integration of Novamente reasoning/learning with AGI-SIM
Nov./Dec. -- Complete first two “infantile stage” tasks: Object permanence Word-object association
Object Permanence
Word-Object Association
Long-Term Novamente Project Goals
Phase One: Definition of design and implementation of initial versions of key components Goal: a teachable AI system capable of embodiment in a simulation world
Phase Two: Refinement of design and implementation in the course of teaching the AI system to control an agent in a simulation world, according to a loosely Piagetan learning plan
Goal: an “artificial child” with qualitatively complex though not humanlike English conversation ability, and the approximate problem-solving ability of an average ten-year old human child within the context of its simulation world
Optionally: Initiate parallel development in “real robotics” via partnership with a robotics research team
Phase Three: Instruction of “artificial child” in relevant topics, including ethics and science
Phase Four: Instruction of AI system in AI design and general computer science Goal: an ethical AI capable of modifying its own implementation with a goal of self-improvement
Credits
Novamente:Cassio PennachinMoshe LooksAri HeljakkaAndre SennaIzabela GoertzelWelter SilvaMichael RossHugo PintoRodrigo Barra
AGI-SIM:
Ari Heljakka
Welter Silva