diff thesis/cortex.org @ 435:ae3bfc82ac7c

on dylan's suggestion, rewriting abstract to show hand more.
author Robert McIntyre <rlm@mit.edu>
date Sun, 23 Mar 2014 17:59:16 -0400
parents 1e5ea711857d
children 853377051f1e
line wrap: on
line diff
     1.1 --- a/thesis/cortex.org	Sun Mar 23 16:38:32 2014 -0400
     1.2 +++ b/thesis/cortex.org	Sun Mar 23 17:59:16 2014 -0400
     1.3 @@ -4,6 +4,51 @@
     1.4  #+description: Using embodied AI to facilitate Artificial Imagination.
     1.5  #+keywords: AI, clojure, embodiment
     1.6  
     1.7 +-- show hand
     1.8 +
     1.9 +* Embodiment is a critical component to Intelligence
    1.10 +
    1.11 +* To explore embodiment, we need a world, body, and senses
    1.12 +
    1.13 +* Because of Time, simulation is perferable to reality
    1.14 +
    1.15 +* Video game engines are a great starting point
    1.16 +
    1.17 +* Bodies are composed of segments connected by joints
    1.18 +
    1.19 +* Eyes reuse standard video game components
    1.20 +
    1.21 +* Hearing is hard; =CORTEX= does it right
    1.22 +
    1.23 +* Touch uses hundreds of hair-like elements
    1.24 +
    1.25 +* Proprioception is the force that makes everything ``real''
    1.26 +
    1.27 +* Muscles are both effectors and sensors
    1.28 +
    1.29 +* =CORTEX= brings complex creatures to life!
    1.30 +
    1.31 +* =CORTEX= enables many possiblities for further research
    1.32 +
    1.33 +* =CORTEX= User Guide
    1.34 +
    1.35 +* Empathy in a simulated worm
    1.36 +
    1.37 +* Embodiment factors action recognition into managable parts
    1.38 +
    1.39 +* Action recognition is easy with a full gamut of senses
    1.40 +
    1.41 +* Digression: bootstrapping with multiple senses
    1.42 +
    1.43 +* \Phi-space describes the worm's experiences
    1.44 +
    1.45 +* Empathy is the process of tracing though \Phi-space 
    1.46 +  
    1.47 +* Efficient action recognition via empathy
    1.48 +
    1.49 +* Contributions
    1.50 +
    1.51 +
    1.52  * Vision 
    1.53  
    1.54    System for understanding what the actors in a video are doing --