Empfohlen
Weitere ähnliche Inhalte
Was ist angesagt?
Was ist angesagt? (20)
Andere mochten auch
Andere mochten auch (12)
Ähnlich wie Ben Goertzel Monash 2011
Ähnlich wie Ben Goertzel Monash 2011 (20)
Mehr von Adam Ford
Mehr von Adam Ford (19)
Kürzlich hochgeladen
Kürzlich hochgeladen (20)
Ben Goertzel Monash 2011
- 1. Ben Goertzel CEO, Novamente LLC and Biomind LLC CTO, Genescient Corp Co-founder, OpenCog Project Vice Chairman, Humanity+ Adjunct Research Professor, Xiamen University, China Advisor, Singularity University and Singularity Institute OpenCog: An Open Source Software Framework & A Design &Vision for Advanced AGI
- 2. Aspects of AGI • Philosophy of Mind • Conception of General Intelligence • Cognitive Architecture • Software Architecture • Environment & Tasks • Developmental Roadmap
- 4. a mind is an evolving, autopoietic, self-referring set of patterns, associated with a system that’s interpreted as goal-achieving -- including patterns in the system and the world (and emergent therebetween), and patterns regarding goal-achievement 2006 2010 2012 (?)
- 6. Artificial General Intelligence (AGI) Humans are, in a certain sense, general-purpose rather than narrowly specialized intelligences… General intelligence may be loosely conceived as “The ability of a system to achieve a variety of complex goals in a variety of complex environments using limited computational resources -- including goals and environments that were not anticipated at the time the system was created.”
- 7. memory prediction perception action goals a mind uses and to do of what will achieve its core operating principle of a general intelligence
- 8. Legg and Hutterʼs Definition of General Intelligence Universal intelligence is a weighted average over all environments, of the intelligence of the agent in that environment The weights assigned to environments are determined by the universal distribution, in which weight of an environment is (exponentially) inversely proportional to the length of the shortest program that computes it (on an assumed reference computer)
- 9. Goertzelʼs Definition of General Intelligence The "pragmatic general intelligence" of an agent is the expected degree to which will achieve the goals specified in a certain goal distribution, in the environments specified in a certain environment distribution
- 10. Goertzelʼs Definition of Efficient General Intelligence The "efficient pragmatic general intelligence" is the expected value over (goal, environment) pairs, of: the expected degree to which the agent will achieve the goal in the environment, normalized by the computational expense it will incur in doing so. In real life, AGI is about making agents with high efficient pragmatic general intelligence relative to relevant classes of goals and environments
- 11. Defining the Intelligence of Real- World Agents • Real-world intelligent systems do not always have explicit rewards or goals • However, they can be locally approximated by goal-oriented systems, during each interval of time, and their intelligence can be estimated via the intelligence of these approximants
- 12. Defining the “Generality” of an Agentʼs Intelligence The extent to which an agentʼs intelligence is general may be defined as the entropy of its environment-specific intelligence, evaluated according to a given prior distribution over environments In this approach the generality of a systemʼs intelligence is orthogonal to its degree of intelligence
- 13. General intelligence in regard to the environments & goals for which humans evolved, and in which humans now operate, involves certain key competencies
- 15. Should we implement AGI via... -- A single core complex cognitive process, supported by others as needed -- Multiple simple processes interacting together, emergently yielding intelligence... ? -- A number of complex cognitive processes, interacting together in a specific way? Glued together perhaps using probabilistic & economic semantics? The human brain seems involve a number of complex processes (modelable as algorithmic), interacting together in specified ways...
- 16. Which is critical? -- The overall cognitive architecture? -- The power of the learning algorithms? -- Both? and they have to synergize well?
- 17. Which is critical? -- The particulars of the system’s explicitly implemented processes and representations? -- The structures and dynamics that emerge via complex self-organization, as the system grows and learns? -- Both? and they have to synergize well?
- 18. MotorSensory Declarative Episodic AttentionalIntentional Procedural OpenPsi DeSTIN (vision / audition) Reward Hierarchy Motor Control Hierarchy robot proxy game proxy memory PLN (inference) Pattern mining concept blending dimensional embedding MOSES Hillclimbing Internal simulation ECAN (economic attention allocation Language processing
- 19. Declarative Probabilistic Logic Networks, concept blending, language comprehension & generation Episodic internal world simulation engine Attentional/ Intentional economic attention networks, adaptive goal hierarchy Sensory hierarchy of memory/ processing units Procedural MOSES (probabilistic evolutionary learning), hillclimbing cognitive synergy in OpenCog In OpenCog, multiple cognitive processes act concurrently on the same knowledge store
- 20. Explicit knowledge representation: Nodes and links (collectively “Atoms”) that explicitly encode individual pieces of knowledge Implicit knowledge representation: Knowledge that is encoded in the coordinated structure or activity of a large set of nodes and links Knowledge Representation in OpenCog
- 21. Nodes are typed and may •symbolize entities in the external world embody simple executable processes •symbolize abstract concepts •serve as components in relationship-webs signifying complex concepts or procedures. Links are typed and may •be binary, unary or n-ary •point to nodes or links; •embody various types of relationships between concepts,percepts or actions. •The network of links is a web of relationships. The two types of OpenCog Atoms: Nodes and Links
- 22. Atoms come with TruthValue and AttentionValue objects TruthValue objects come in several forms, e.g. Single probability values SimpleTruthValues, consisting of (probability, count) pairs IndefiniteTruthValues, consisting of tuples (Lower bound, Upper bound, confidence) DistributionalTruthValues, each encompassing a first or second order probability distribution AttentionValue objects contain information telling how much processor time and memory an Atom should get. Most simply an AttentionValue object contains ShortTermImportance (STI) value telling how much processor time the Atom should get in the near future LongTermImportance (LTI) value telling how important it is to retain the Atom in memory VLTI bit telling whether, if the Atom is removed from RAM, it should be kept on disk
- 23. Each type has its own semantics Informally, we may divide the node types into multiple “varieties” The precise collection of Atom types has changed over the years as we have developed the OpenCog system Someday, a future version may learn its own Atom types
- 24. There are multiple types of Links Each type has its own semantics Informally, we may divide the link types into multiple “varieties”
- 25. Member Ben_Goertzel Goertzel_Family Member Anchovy_Goertzel Goertzel_Family <.8> ("Anchovy" is a rabbit, so her membership degree in the Goertzel family is less than 1)
- 26. AsymmetricHebbianLink Ben_Goertzel insane <.5> (this means that when "Ben Goertzel" is mentioned, "insane" is often also mentioned) SymmetricHebbianLink dog pet SymmetricHebbianLink ConceptNode: dog ConceptNode: pet ContextLink USA SymmetricHebbianLink dog pet <.8> ContextLink Korea SymmetricHebbianLink dog pet <.5>
- 27. ExecutionLink + ListLink 2 3 5 ExecutionLink SchemaNode: + ListLink NumberNode: 2 NumberNode: 3 NumberNode: 5 ExecutionLink kick ball_44 ExecutionLink SchemaNode: kick SemeNode: ball_44 ExecutionLink give ListLink (ChenShuo, ball_44)
- 28. InheritanceLink cat animal InheritanceLink animal cat <.01> InheritanceLink animal cat <.01,.95> SubsetLink parrot human <0> IntensionalInheritanceLink parrot human <.6> IntensionalInheritanceLink frog human <.03>
- 29. EvaluationLink <.8> PredicateNode: is_silly SemeNode: Ben_Goertzel ForAllLink VariableNode: $X, $Y ImplicationLink <.7> AndLink InheritanceLink $X man InheritanceLink $Y woman EvaluationLink love ListLink ($X, $Y) EvaluationLink overestimate <.9> ListLink $X EvaluationLink beauty $X Ben Goertzel is silly When a man loves a woman, he greatly overestimates her beauty
- 30. MindAgents are objects that act on the Atomspace: modifying, adding and/or removing Atoms MindAgents’ activities are scheduled by a Scheduler: the simplest Scheduler would just cycle through all available MindAgents OpenCog involves a carefully constructed combination of MindAgents, intended to reinforce rather than confuse each other!
- 31. MOSES Probabilistic Evolutionary Learning Combines the power of two leading AI paradigms: evolutionary and probabilistic learning Extremely broad applicability. Successful track record in bioinformatics, text and data mining, and virtual agent control. Moshe Looks 2006 PhD thesis: metacog.org Probabilistic Logic Networks A highly general, practical integration of probability theory and symbolic logic. Extremely broad applicability. Successful track record in bio text mining, virtual agent control. Based on mathematics described in Probabilistic Logic Networks, published by Springer in 2008 Two Key Algorithms for Procedural and Declarative Knowledge Creation
- 32. Concept Blending
- 34. Economic Attention Allocation Each node or link in the AtomSpace is tagged with a probabilistic truth value, and also with an “attention value”, containing Short-Term Importance and Long-Term Importance components. An artificial-economics-based process is used to update these attention values dynamically -- a complex, adaptive nonlinear process.
- 35. Psi Architecture Overview figure from “Principles of Synthetic Intelligence” by Joscha Bach
- 36. Symbol Grounding in Psi figure from “Principles of Synthetic Intelligence” by Joscha Bach
- 37. Joscha Bach’s MicroPsi Architecture figure from “Principles of Synthetic Intelligence” by Joscha Bach Basic net-entity from which MicroPsi’s node types, comprising its dynamic knowledge representation, are composed
- 38. Psi OpenCog Memory AtomSpace (weighted semantic hypergraph), Procedure repository, space/time index servers, etc. Demands Implemented as GroundedPredicateNodes Urges Called “Ubergoals”, these are also GPNs, with truth values calculated in terms of corresponding Demands Urgency For goal Atoms, the ShortTermImportance value indicates urgency Pleasure A GPN whose internal TV evaluation function compares actual to expected levels of Ubergoal satisfaction Goals Atoms (both Ubergoals and learned subgoals) in the system’s GoalPool Motive Selection Carried out as a function of Economic Attention Allocation, which dispenses STI funds to goals Action Selection Similar to in Psi, OpenPsi selects composite procedures to execute based on its inferences of what may best achieve its goals Planning Arises as a consequence of multiple cognitive processes, including PLN, MOSES and ECAN Modulators (e.g. activation, resolution level, certainty, selection threshold) System parameters, representable as GPNs, with TVs estimated by appropriate heuristic formulae
- 39. Other approaches, e.g. Itamar Arel’s DeSTIN, follow similar principles with different details -- a general term I’ve used is “compositional spatiotemporal deep learning networks”. These may be hybridized with OpenCog.
- 40. adviceinput below belowbelow between aligned on axis perpendicular to mouth-nose-eyes axis ... visual patterns (e.g. DeSTIN centroids) corresponding to the semantic perception node linked to “human eye” concept node phrase node “human eye” reference link PERCEPTUAL CSDLN SEMANTIC-PERCEPTUAL CSDLN COGNITIVE SEMANTIC NETWORK reference link reference link semantic HTM nodes/links formed by pattern mining perceptual HTM semantic HTM provides probabilistic biasing to perceptual HTM aligned on axis perpendicular to eyes axis CSDLN = “Compositional Spatiotemporal Deep Learning Network, e.g. HTM, DeSTIN,...
- 41. grasp object The motoric hierarchy node corresponding to a particular set of servomotors, might for instance contain clusters of paths through configuration space that the servomotors have historically followed. MOTORIC CSDLN SEMANTIC- MOTORIC CSDLN rotate arm toward object raise or lower arm toward object raise or lower arm toward default position after after before/after/ simultaneous get object advice input COGNITIVE SEMANTIC NETWORK “get” phrase nodeconcept node reference link reference link reference link motor patterns (e.g. centroids) corresponding to the semantic motoric node “raise or lower arm toward object”
- 42. SEMANTIC- MOTORIC CSDLN SEMANTIC-PERCEPTUAL CSDLN SEMANTIC GOAL CSDLN COGNITIVE SEMANTIC NETWORK possess food eat food maintain appropriate fullness get object (e.g. food) see food & get food --> possess food see food see meat see sandwich ... ... “get”Hungry & eat food --> maintain appropriate fullness
- 43. How ---> Helps | |/ Map formation Goal system Simulation Sensorimotor pattern recognition Uncertain inference Creates new concepts and relationships, enabling briefer useful inference trails Goal refinement enables more careful goal-based inference pruning - Simulations provide a method of testing speculative inferential conclusions - Simulations suggest hypotheses to be explored via inference Creates new concepts and relationships, enabling briefer useful inference trails Supervised procedure learning Creates new procedures to be used as modules in candidate procedures Goal refinement allows more precise definition of fitness functions, making procedure learningʼs job easier Simulation provides a method of “fitness estimation” allowing inexpensive testing of candidate procedures Extraction of sensorimotor patterns allows creation of abstracted fitness functions for (inferentially and simulatively) evaluating procedures guiding real-world actions Attention allocation Creates new concepts grouping “attentionally related” memory items, enabling AA to find subtler attentional patterns involving these nodes Goal refinement allows more accurately goal- driven allocation of attention Simulation provides data for attention allocation -- allowing attentional information to be extracted from co- occurences observed in simulation Creates concepts grouping “attentionally related” memory items, enabling AA to find subtler attentional patterns involving these nodes Concept creation Creates new concepts to be fed into other concept creation mechanisms Goal refinement provides more precise definition of criteria via which new concepts are created Utility of concepts may be assessed via creating simulated entities embodying the new concepts and seeing what they lead to in simulation Creates new concepts to be fed into other concept creation mechanisms
- 44. How ---> Helps | |/ Uncertain inference Supervised procedure learning Attention allocation Concept creation Uncertain inference NA When inference gets stuck in an inference trail, it can ask procedure learning to learn new patterns regarding concepts in the inference trail (if there is adequate data regarding the concepts) Importance levels allow pruning of inference trees Provides new concepts, allowing briefer useful inference trails Supervised procedure learning Inference can be used to allow prior experience to guide each instance of procedure learning. NA Importance levels may be used to bias choices made in the course of procedure learning (e.g. in OCP, in the fitness evaluation and representation-building phases of MOSES) Provides new concepts, allowing compacter programs using new concepts in various roles Attention allocation Enables inference of new HebbianLinks and HebbianPredicates from existing ones Procedure learning can recognize patterns in historical system activity, which are then used to build concepts and relationships guidng attention allocation NA Combination of concepts formed via map formation, may lead to new concepts that even better direct attention Concept creation Allows inferential assessment of the value of new concepts Procedure learning can be used to search for high-quality blends of existing concepts (using e.g. inferential and attentional knowledge in the fitness functions) Allows assessment of the value of new concepts based on historical attentional knowledge NA
- 45. How ---> Helps | |/ Uncertain inference Supervised procedure learning Attention allocation Concept creation Map formation Speculative inference can help map formation guess which maps to hunt for Procedure learning can be used to search for maps that are more complex than mere “co- occurrence” Attention allocation provides the raw data for map formation No significant direct synergy Goal system Inference can carry out goal refinement No significant direct synergy Flow of importance among subgoals determines which subgoals get used, versus being forgotten Concept creation can be used to provide raw data for goal refinement (e.g. a new subgoal that blends two others) Simulation In order to provide data for setting up simulations, inference will often be needed No significant direct synergy Attention allocation tells which portions of a simulation need to be run in more detail No significant direct synergy Sensorimotor pattern recognition Speculative inference helps fill in gaps in sensory data Procedure learning can be used to find subtle patterns in sensorimotor data Attention allocation guides pattern recognition via indicating which sensorimotor stimuli and patterns tend to be associatively linked New concepts may be created that then are found to serve as significant patterns in sensorimotor data
- 46. How ---> Helps | |/ Map formation Goal system Simulation Sensorimotor pattern recognition Map formation NA Map formation may focus on finding maps related to subgoals, and good subgoal refinement helps here No significant direct synergy No significant direct synergy Goal system Concepts formed from maps may be useful raw material for forming subgoals NA No significant direct synergy No significant direct synergy Simulation No significant direct synergy No significant direct synergy NA Presence of recognized sensorimotor patterns may be used to judge whether a simulation is sufficiently accurate Sensorimotor pattern recognition Concepts formed from maps may usefully guide sensorimotor pattern search Directing pattern search toward patterns pertinent to subgoals, may make the task far easier Patterns recognized in simulations may then be checked for presence in real sensorimotor data NA
- 50. Currently the OpenCog “core (AtomSpace, scheduler, comms, saving to disk, etc.) is C++ for Unix, with an STL-based API MindAgents are currently coded in C++ or Python. Some MindAgents also invoke external Java processes
- 55. How Important Is Embodiment? Some AI theorists believe that robotic embodiment is necessary for the achievement of powerful AGI Others believe embodiment is entirely unnecessary We believe embodiment is extremely convenient for AGI though perhaps not strictly necessary; and that virtual-world embodiment is an important, pragmatic and scalable approach to pursue alongside physical-robot embodiment
- 56. Current virtual world platforms have some fairly severe limitations, which fortunately can be remedied with effort Object-object interactions are oversimplified, making tool use difficult Agent control relies on animations and other simplified mechanisms, rather than having virtual servomotors associated with each joint of an agent’s skeleton
- 57. Partial solution: Integration of a robot simulator with a virtual world engine Player / Gazebo: 3D robot control + simulation framework OpenSim: open-source virtual world It seems feasible to replace OpenSim’s physics engine with appropriate components of Player/Gazebo, and make coordinated OpenSim client modifications +
- 58. Current Virtual Worlds lack fluids, powders, pastes, fabrics … they donʼt completely implement “naïve physics”
- 59. One likely solution: bead physics Spherical beads with specially designed adhesion properties can emulate fluids, fabrics, pastes, strings, rubber bands, etc. Bead physics can be added to virtual world physics engines
- 60. Possible solution: build robots from “macrocells” -- flexible ball-like units that can stretch into different shapes, sense the environment, and pass power and information to each other Current robots are made mainly of inert parts -- very few of their parts are sensors or actuators...
- 63. This shows OpenCog oscillating between the robot's "home" and batteries, as a result of its quests to fulfill integrity and energy demands respectively. After a few movements back and forth, it also shows the Psi monitor updating graphs of the Psi variables (note the updates are synchronized between graphs).
- 64. This video shows OpenCog spelled out in blocks, as a 3D path finding mission. It also shows the demand for finding a battery to restore energy. Subsequent to finding the battery, the avatar asks the player for a battery. The player then pushes a button to make one appear. A video transition happens where some footage was cut out (involving more observations of the button generating food), and the video then shows the OpenCog avatar using the button to create food for itself.
- 67. Piagetan Stages of Development
- 68. Piaget Meets Uncertain Inference
- 69. • 2011-2012:A Proto-AGIVirtual Agent • 2013-2014:A Complete, Integrated Proto-AGI Mind (Piagetan concrete) • 2015-2016:Advanced Learning and Reasoning (Piagetan formal) • 2017-2018: AGI Experts • 2019-2021: Full-On Human Level AGI • 2021-2023: Advanced Self-Improvement (Piagetan reflexive)
- 70. • 6 month from start (now): Unity-based minecraft-like world initially built, proxy to Unity built, 3D pathfinding, frequent subgraph miner designed/built, PLN and “embodiment” (body-control) systems debugged/refactored, PLN based planner built, OpenPsi motivation/emotion system implemented • 12 month (end of 2011): New artwork/animations integrated into world, further behaviors/interactions for objects scripted/tested, PLN further refactored and simple temporal/spatial reasoning integrated, reinforcement/imitation learning integrated (and interface btw this learning and OpenPsi created), dialogue system refactored/ improved, appropriate emotional responses demostrated. Reliable live demo! • 18 month (mid-2012):Attention allocation integrated, complex planning demonstrated, learning & reasoning integrated, linguistic question answering and command demonstrated. Exciting live demo... • 24 month (end of 2012): Software toolkit built out to enable tractable integration into games. Demo improvements. OpenCog 1.0 release. Intelligence improvements OpenCog Hong Kong Project
- 71. • 2010: Simplistic integration of OpenCog with Nao robot for navigation, command- following; implementation of English language generation for OpenCog • 2011: Re-implementation of Itamar Arel’s team’s DeSTIN architecture in CUDA for GPU computing: initial version completed June 2011, refinements underway • 2012-13: Integration of DeSTIN with OpenCog using intermediate “semantic compositional spatiotemporal deep learning network”; integration of robotic movement control system with OpenCog • 2013-2014: OpenCog-powered intelligent robotics Xiamen University BLISS Lab
- 73. biomedical informatics financial prediction / analytics video games / virtual worlds robot toys service robots information retrieval etc. !!!
- 74. The natural synergy between advanced AI and gaming/ virtual worlds has been avidly discussed for at least a decade, and is now finally becoming a practical reality
- 75. For a readable journalistic treatment of the application of machine learning to study longevity in fruit flies, see “AIs, Superflies and the Path to Immortality” in H+ Magazine, hplusmagazine.com Ensemble based machine learning does well here, but appropriate OpenCog integration could do much better by allowing a vast variety of available bio datasets to be brought to bear on the analysis of any one dataset.