designing artificial minds n.
Download
Skip this Video
Download Presentation
Designing Artificial Minds

Loading in 2 Seconds...

play fullscreen
1 / 29

Designing Artificial Minds - PowerPoint PPT Presentation


  • 103 Views
  • Uploaded on

Designing Artificial Minds. Harri Valpola. Computational neuroscience group Laboratory of computational engineering Helsinki University of Technology http://www.lce.hut.fi/~harri/. “The great end of life is not knowledge but action” — Thomas Henry Huxley (1825-1895).

loader
I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
capcha
Download Presentation

PowerPoint Slideshow about 'Designing Artificial Minds' - fionnula-scanlan


Download Now 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.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
designing artificial minds
Designing Artificial Minds

Harri Valpola

Computational neuroscience group

Laboratory of computational engineering

Helsinki University of Technology

http://www.lce.hut.fi/~harri/

Computational Neuroscience Group, LCE

Helsinki University of Technology

slide2
“The great end of life is not knowledge but action”

—Thomas Henry Huxley (1825-1895)

Computational Neuroscience Group, LCE

Helsinki University of Technology

sea squirts our distant cousins
Sea Squirts — Our Distant Cousins
  • Sea-squirts are common marine animals
  • Two stages of development: larva and adult
  • Larvae look very much like tadpoles

Picture:

http://www.jgi.doe.gov/News/ciona_4panel.jpg

Computational Neuroscience Group, LCE

Helsinki University of Technology

no movement no brain
No Movement  No Brain

Picture:

http://www.gulfspecimen.org/images/LeatherySeaSquirt.jpg

Computational Neuroscience Group, LCE

Helsinki University of Technology

smooth elegant skillful
Smooth, Elegant, Skillful

Picture:

http://www.africanbushsafaris.com/fotos%20touren/Oryx.jpg

Picture:

http://www.ebroadcast.com.au/blahdocs/uploads/tiger_running_sml_2784.jpg

Computational Neuroscience Group, LCE

Helsinki University of Technology

evolution of the motor system
Evolution of the Motor System
  • Spinal cord: “simple” reflexes and rhythmic movement
  • Brain stem: more complex reflexes
  • Cerebellum / midbrain structures: complex motor coordination
  • Basal ganglia: action selection
  • Hippocampal formation: navigation
  • Neocortex: integration and planning

Computational Neuroscience Group, LCE

Helsinki University of Technology

methods
Methods
  • Synthetic approach: learning by building
  • Neural network simulations
  • Real and simulated robots

Computational Neuroscience Group, LCE

Helsinki University of Technology

early motor system
Early Motor System
  • Spinal cord: “simple” reflexes and rhythmic movement
  • Brain stem: more complex reflexes
  • Cerebellum / midbrain structures: complex motor coordination
  • Basal ganglia: action selection
  • Hippocampal formation: navigation
  • Neocortex: integration and planning

Computational Neuroscience Group, LCE

Helsinki University of Technology

prediction and anticipation
Prediction and Anticipation

Computational Neuroscience Group, LCE

Helsinki University of Technology

adaptive motor control based on a cerebellar model
Adaptive Motor Control Based on aCerebellar Model

Computational Neuroscience Group, LCE

Helsinki University of Technology

prediction and anticipation1
Prediction and Anticipation

Computational Neuroscience Group, LCE

Helsinki University of Technology

self supervised learning in control
Self-Supervised Learning in Control
  • Corrections are made by a large number of “reflexes” (spinal cord, brain stem, cortex / basal ganglia).
  • Cerebellar system learns to control using the reflexes as teaching signals.

Picture of cerebellar system

Computational Neuroscience Group, LCE

Helsinki University of Technology

reflexes
Reflexes

Stretch reflex

Opto-kinetic reflex

Picture:

http://www.inma.ucl.ac.be/EYELAB/neurophysio/perception_action/vestibular_optokinetic_reflex_fichiers/image004.jpg

Picture:

http://www.cs.stir.ac.uk/courses/31YF/Notes/musstr.jpg

Computational Neuroscience Group, LCE

Helsinki University of Technology

robot reflex
Robot “Reflex”

Computational Neuroscience Group, LCE

Helsinki University of Technology

the cerebellar system
The Cerebellar System

Picture of cerebellar cortex

Computational Neuroscience Group, LCE

Helsinki University of Technology

long term depression ltd guided by climbing fibres
Long-Term Depression (LTD) Guided by Climbing Fibres

Picture of LTD in Purkije cells

Computational Neuroscience Group, LCE

Helsinki University of Technology

vestibulo ocular reflex
Vestibulo-Ocular Reflex

Picture:

http://www.uq.edu.au/nuq/jack/VOR.jpg

Computational Neuroscience Group, LCE

Helsinki University of Technology

system level computational neuroscience
System-Level Computational Neuroscience

Questions to be answered:

  • What kind of components are needed for a cognitive architecture?
  • What are different algorithms good for and how they can be combined?

The brain is a good solution to these questions  Try to

understand its algorithms on system level (level of behaviour)

Computational Neuroscience Group, LCE

Helsinki University of Technology

slide19
“Without knowledge action is useless and action without knowledge is futile”

—Abu Bakr (c. 573-634)

Computational Neuroscience Group, LCE

Helsinki University of Technology

components for a cognitive system
Components for a Cognitive System

Basal ganglia: selection, reinforcement learning (trial-and-error learning)

Hippocampal formation: one-shot learning, navigation, episodic memory

Neocortex:

  • Represents the state of the world — including oneself
  • Invariant representations, concepts
  • Attention / selection (both sensory and motor)
  • Simulation of potential worlds = planning and thinking
  • Relations and other structured representations (akin to symbolic AI)

Computational Neuroscience Group, LCE

Helsinki University of Technology

neocortex
Neocortex
  • A hierarchy of feature maps: increasing levels of abstraction
  • Bottom-up and top-down/lateral inputs treated differently
  • Local competition
  • Long-range reciprocal excitatory connections

Picture:

http://www.pigeon.psy.tufts.edu/avc/husband/images/Isocrtx.gif

Computational Neuroscience Group, LCE

Helsinki University of Technology

representations for natural images by independent component analysis ica
Representations for Natural Images by Independent Component Analysis (ICA)
  • http://www.cis.hut.fi/projects/ica/imageica/
  • ICA is an example of ..unsupervised learning.
  • Can learn something like .. V1 simple cells.

Computational Neuroscience Group, LCE

Helsinki University of Technology

invariant features
Invariant features
  • Group simple features into complex in a hierarchical model.

Picture:

http://cs.felk.cvut.cz/~neurony/neocog/en/images/figure3-1.gif

Computational Neuroscience Group, LCE

Helsinki University of Technology

complex cells from images
”Complex Cells” from Images

Computational Neuroscience Group, LCE

Helsinki University of Technology

abstractions and meaning
Abstractions and Meaning

Computational Neuroscience Group, LCE

Helsinki University of Technology

abstractions and meaning1
Abstractions and Meaning
  • Once we have motor output, we can learn which information is important and meaningful

Left camera

Right camera

Computational Neuroscience Group, LCE

Helsinki University of Technology

relevance to human enhancement
Relevance to Human Enhancement

How about mind prostheses? New senses (like web-sense)?

Knowing how the brain works would certainly be useful for prostheses, but for healthy persons…

  • Input to the brain is easiest to deliver through existing senses — content matters, not the channel
  • Output from the brain through motor system is more limited  implanted electrodes might surpass this capacity
  • I expect intelligent tools to be far more common than prosthetic devices for a long time, but this doesn’t mean their societal impact would be any smaller

Computational Neuroscience Group, LCE

Helsinki University of Technology

slide28

Brain is a good solution for an engineering problem

Neuroscience

Picture:

http://britton.disted.camosun.bc.ca/escher/drawing_hands.jpg

Technology

Computational Neuroscience Group, LCE

Helsinki University of Technology

kiitos thank you
KIITOS! THANK YOU!

Computational Neuroscience Group, LCE

Helsinki University of Technology