1 / 18

Machines like us

Machines like us. Steve Grand Cyberlife Research Ltd. Hon. Fellow: Psychology, Cardiff Biomimetics, Bath steve@cyberlife-research.com www.cyberlife-research.com. The missing algorithm of thought. Computational approach hasn’t achieved much in 30 years or more The model is not the system

salim
Download Presentation

Machines like us

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. Machineslike us Steve Grand Cyberlife Research Ltd. Hon. Fellow: Psychology, Cardiff Biomimetics, Bath steve@cyberlife-research.com www.cyberlife-research.com

  2. The missing algorithm of thought • Computational approach hasn’t achieved much in 30 years or more • The model is not the system • Random abstractions • Combining incompatible solutions • Insufficient attention to grounding • What we need is a breakthrough • We have one existence proof but we don’t know how it works • Biology may use some unfamiliar principles

  3. Methodology: What we need here is a robot orang-utan… • Biologically plausible (neither slavish nor abstract) • Physical robot in complex environment • Human-style (mammal-style) intelligence, not human-level • Self-organising architecture – find the meta-machine • Work solo & assume nothing

  4. Lucy MkI Vision (monocular) Hearing (binaural) Anamorphic retina Cochlea(frequency discrimination) Ganglion cells (contrast/motion) Lateral superior olive(phase discrimination) Superior colliculus(visual saccades) Muscles 13 degrees of freedom Voice Virtual antagonistic pairs of compliant muscles Virtual/electronic model of vocal tract: Lungs (volume, flow, pressure)vocal cords, glottis, mouth resonance Proprioceptors for sensing joint position & motion Onboard computers Other sensors 5 x 16-bit sensory processors with shared memory 2 x 8-bit motor processors Plus desktop PC for brain modelling Touchtemperaturebalance/motionenergy consumption

  5. Inside the brain of an AI researcher… Feature abstraction Command sequences MUSCLES SENSES Binding Discrete signal paths Feed-forward Genetically specified Ad hoc architectures (Feedback)

  6. McCulloch and who? Feedforward BUT… So much traffic goes the wrong way The wiring diagram doesn’t work Discrete circuitry BUT… Neurons are promiscuous Hard-wired BUT… Scotomas heal too quickly God didn’t design beaches Ad-hoc & Specialised modules BUT… Cortex is cortex is cortex Refining and combining BUT… No place where it all comes together No data can be lost through abstraction

  7. anticipation attention intention YANG(model) desire “Mental” state sense YIN(reality) expectation/attention intention sensation feedback Actual (sensory) state Servos: a model ofthe world?

  8. Upgoing Downcoming I II, III IV V, VI Upcoming Downgoing ? Senses ? ? ? ?

  9. Lucy’s brain EYES • Yin/yang servos • Active vision • Morphs • Bandwidth • Symbols EYE MUSCLES YIN YANG Hippocampus limbic feedback direction PROPRIOCEP-TORS Cortex VIRTUAL SENSORS VOLUNTARY MUSCLES Sub-cortex SYMBOLS???

  10. Buildup Direct from LGN (motion) Saccade targetEye-relative96 x 96 V1 infragranular(isolated boundary?) Gaze angle Transform Dome buildup96 x 96 Gain fieldgaze + targ =body-centred targ96 x 96 Proprio map Motor map Head & eye4 X 4 Head & eye4 X 4 Neck & ocular proprioceptors Neck & ocular muscles Environmental coupling Lucy’s Superior Colliculus

  11. Lucy learning her lines But is this really just the start of a feature extraction pipeline? Is it primarily a cortical extension of the saccade reflex

  12. Extending the frog? Right hemifield Left hemifield Old motion-sensitive system Remove xlation dimension Remove rotation & scale dimensions SC (optic tectum) V1 ‘V2’? Retinotopic frame Object-centred X,Y Object-Centred X,Y,Z,R

  13. Camera Anamorphic Centre/surround RETINA Infragranular Supragranular Layer IV V1 WTA Saccade target96 x 96 Boundary resonance & isolation96 x 96 Orientation bias96 x 96 Inhibition / normalisation Intrinsic excitation Short-range excitationLong-range inhibition Superior Colliculus(Saccade target) V2(bounded surface) From V2(attentional prime) Initial RFs RFs after learning Vertical lines only

  14. From V1 Cytochrome Oxidase Concentric Radial Layer IV V2 Fusion of orientation columns into macrocolumns32 X 32 Summation & wave synchronisation –rotation invariance Travelling waves – scale invariance Concentric inhibitory Concentric excitatory Prime – wave synchronisation Signature map Embyological wiring from test-card signals Correlated time signatures – surface classification To V4 etc. Hypothetical “V2 + MT” To V1 attentional prime Local excite / long-range inhibit

  15. Coordinate morphs Auditory Motor TEST-CARD SIGNALS Visual

  16. EYES EYE MUSCLES V1 S1 Map of maps??? YIN YANG THALAMUS Hippocampus retina skin • Bandwidth hogging • Always thinking of something • Episodic  semantic memory migration PROPRIOCEP-TORS Cortex VIRTUAL SENSORS VOLUNTARY MUSCLES Sub-cortex SYMBOLS??? Virtual pebbles, maps of maps, and the bandwidth of conscious attention

  17. Lucy MkII Better muscle dynamics, vision, hearing, manipulators More computer power A pain in the ass

  18. Subliminal plugfor my books www.cyberlife-research.com Weidenfeld & Nicolson Very modestly priced! Thanks to for supporting the Lucy project

More Related