1 / 27

Cognitive Robotics and Global Workspace Theory

Cognitive Robotics and Global Workspace Theory. Murray Shanahan Imperial College London Department of Computing. Overview. Global workspace theory (GWT) GWT and the frame problem A cognitive architecture using a global workspace. Global Workspace Theory. Parallel Unconscious

Download Presentation

Cognitive Robotics and Global Workspace Theory

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Cognitive Robotics and Global Workspace Theory Murray Shanahan Imperial College London Department of Computing

  2. Overview Global workspace theory (GWT) GWT and the frame problem A cognitive architecture using a global workspace

  3. Global Workspace Theory

  4. Parallel Unconscious Specialist Processes Global Workspace Global Workspace Architecture Multiple parallel specialist processes compete and co-operate for access to a global workspace If granted access to the global workspace, the information a process has to offer is broadcast back to the entire set of specialists

  5. Conscious vs Non-Conscious • Global workspace theory (Baars) hypothesises that the mammalian brain instantiates such an architecture • It also posits an empirical distinction between conscious and non-conscious information processing • Information processing in the parallel specialists is non-conscious • Only information that is broadcast is consciously processed

  6. Embodiment • According to GWT, only something that instantiates a global workspace architecture is capable of conscious information processing • But this is a necessary not a sufficient condition • I have argued (Shanahan, 2005) that the architecture must direct the actions of a spatially localised body using a sensory apparatus fastened to that body • This allows the set of parallel specialists a shared viewpoint, from which they can be indexically directed to the world and fulfil a common remit

  7. Empirical Evidence • Contrastive analysis compares and contrasts closely matched conscious and unconscious brain processes • Dehaene, et al. (2001) • Imaged subjects being presented with “masked” words • Masked and visible conditions compared • Such experiments suggest that conscious information processing recruits widespread brain resources while unconscious processing is more localised

  8. Neural Parallelism • An animal’s nervous system is massively parallel • Masssive parallelism surely underpins human cognitive prowess • So how are the massively parallel computational resources of an animal’s central nervous system harnessed for the benefit of that animal? • How can they orchestrate a coherent and flexible response to each novel situation? • Nature has solved this problem. How?

  9. Serial from Parallel / Unity from Multiplicity • The global workspace architecture supplies a possible answer • The global workspace itself exhibits a serial procession of states • Yet each state-to-state transition is the result of filtering and integrating the contributions of huge numbers of parallel computations • The global workspace architecture thereby distils unity out of multiplicity • ( This is perhaps the essence of consciousness, of what it means to be a singular, unified subject )

  10. The Frame Problem

  11. The Frame Problem (1) • The frame problem orginated in classical AI • This is tricky, but was more-or-less solved in the mid 1990s • Our concern is the wider interpretation given to the frame problem by philosophers, notably Dennett and Fodor How can we formalise the effects of actions in mathematical logic without having to explicitly enumerate all the trivial non-effects?

  12. The Frame Problem (2) • Fodor’s version: • A cognitive process is informationally unencapsulated if it has the potential to draw on information from any domain • Analogical reasoning is the epitome of informational unencapsulation How do informationally unencapsulated cognitive processes manage to select only the information that is relevant to them without having to explicitly consider everything an agent believes ?

  13. Computational “Infeasibility” • Fodor claims that informationally unencapsulated cognitive processes are computationally infeasible • Fodor believes that this is a fatal blow for cognitive science as we know it because it entails we cannot find a computational explanation of the human mind’s “central systems” “ The totality of one’s epistemic commitments is vastly too large a space to have to search … whatever it is that one is trying to figure out. ” (Fodor, 2000)

  14. Fodor’s Modularity of Mind The mind’s peripheral processes are special purpose, do things like parsing and low-level vision, and are computational The mind’s central processes are general purpose, do things like analogical reasoning, are informationally unencapsulated, and probably aren’t computational “… it probably isn’t true that [all] cognitive processes are computations. … [so] it’s a mystery, not just a problem, what model of the mind cognitive science ought to try next. ” (Fodor, 2000)

  15. Peripheral Processes (Modules) B B B C C C D D D A A A “Is C relevant? Yes!” “Is A relevant?” “Is B relevant?” Central Processes GWT and the Frame Problem (1) • Both Fodor and Dennett seem to have a strictly serial architecture in mind when they characterise the frame problem This certainly looks computationally infeasible

  16. “Am I relevant? Yes!” Parallel Unconscious Specialists “Am I relevant?” C C B B “Am I relevant?” “Am I relevant?” D A D A Global Workspace GWT and the Frame Problem (2) • But global workspace architecture offers a parallel alternative (Shanahan & Baars, 2005) In the context of an appropriate parallel architecture, the frame problem looks more manageable

  17. Analogical Reasoning (1) • Analogical reasoning is informational unencapsulation in its purest form • Computational models of analogical reasoning distinguish between • retrieval – the process of finding a potential analogue in long-term memory for a representation already in working memory – and • mapping – the subsequent process of finding correspondences between the two “Analogical reasoning depends precisely upon the transfer of information among cognitive domains previously assumed to be irrelevant ” (Fodor)

  18. Analogical Reasoning (2) • Retrieval is the locus of the frame problem in analogical reasoning • One of the most psychologically plausible computational models is LISA (Hummel & Holyoak), which mixes serial and parallel computation, and also fits a global workspace architecture very closely LISA GWT Serial presentation in global workspace Contents of GW Broadcast of GW contents Unconscious parallel processes Serial presentation in working memory Active proposition in WM Parallel activation in long-term memory Distributed propositions in LTM

  19. A GWT-Based Cognitive Architecture

  20. The Simulation Hypothesis “Thought is internally simulated interaction with the environment” (Cotterill, 1998) • Internal simulation is integral to our inner life and facilitates anticipation and planning • Three assumptions (Hesslow, 2002) • The brain’s motor centres can be active without producing overt action • The brain’s perceptual apparatus can be active without the presence of external stimuli • Internally generated motor activity can elicit internally generated perceptual activity through associative mechanisms

  21. Cortical area 1 Cortical area 2 Cortical area 3 GW Broadcast Selection / competition Combining a GW with Internal Simulation It’s possible to combine an internal sensorimotor loop with mechanisms for broadcast and competition, and thereby marry the simulation hypothesis with global workspace theory

  22. Global neuronal workspace Column 1 Column 3 Column 2 A Biologically Non-implausible Implementation Built out of spiking neurons with transmission delays Cortical columns comprise 32  32 fully connected nets Workspace nodes comprise 16  16 topographically mapped regions Cortical columns trained to associate successively presented pairs of images using STDP

  23. Controlling a Robot • The inner sensorimotor loop can be embedded in a larger system and used to control a robot • This results in a form of “cognitively-enhanced” action selection • The implemented action selection architecture • Is based on salience and winner-takes-all • Imposes a veto at final motor output stage • Modulates salience as a result of internal simulation • Releases veto when salience exceeds a threshold • The parallelism of the GW architecture enables the inner loop to explore alternatives

  24. Am AC1b AC1a VC / IT GW / BG AC2b AC2a AC3b AC3a The “Core Circuit” VC / IT = visual cortex / inferior temporal cortex AC = association cortex GW / BG = global workspace / basal ganglia Am = amygdala

  25. A Proof-of-Concept Experiment NRM model Webots simulator Motor Cortex Camera input Salience populations Khepera Association Cortex Camera view Reward & punishment Motor veto Motor output Global Workspace

  26. Concluding Remarks • Combination of GW architecture and internal simulation is a promising non-classical-AI approach to cognitive robotics • Shortcomings of current work • Use of biologically non-plausible neuron model • Use of attractor net to model global workspace • Dynamically uninteresting robot • Ongoing and future work • New model of core circuitry (partly achieved) • Realistic spiking neurons • Broadcast through resonance and synchrony • Dynamically complex robot (eg: CRONOS)

  27. References Shanahan, M.P. & Baars, B.J. (2005). Applying Global Workspace Theory to the Frame Problem, Cognition 98 (2), 157–176. Shanahan, M.P. (2005). Global Access, Embodiment, and the Conscious Subject, Journal of Consciousness Studies 12 (12), 46–66. Shanahan, M.P. (2006). A Cognitive Architecture that Combines Inner Rehearsal with a Global Workspace, Consciousness and Cognition15, 433–449.

More Related