comparison thesis/abstract.org @ 551:d304b2ea7c58

some changes from winston.
author Robert McIntyre <rlm@mit.edu>
date Fri, 02 May 2014 13:40:47 -0400
parents 8e52a2802821
children
comparison
equal deleted inserted replaced
550:b1d8d9b4b569 551:d304b2ea7c58
7 7
8 To attack the action recognition problem, I developed a computational 8 To attack the action recognition problem, I developed a computational
9 model of empathy (=EMPATH=) which allows me to recognize actions using 9 model of empathy (=EMPATH=) which allows me to recognize actions using
10 simple, embodied representations of actions (which require rich 10 simple, embodied representations of actions (which require rich
11 sensory data), even when that sensory data is not actually available. 11 sensory data), even when that sensory data is not actually available.
12 The missing sense data is ``imagined'' by the system by combining 12 The missing sense data is imagined by combining previous experiences
13 previous experiences gained from unsupervised free play. The worm is a 13 gained from unsupervised free play. The worm is a five-segment
14 five-segment creature equipped with touch, proprioception, and muscle 14 creature equipped with touch, proprioception, and muscle tension
15 tension senses. It recognizes actions using only proprioception data. 15 senses. It recognizes actions using only proprioception data.
16 16
17 In order to build this empathic, action-recognizing system, I created 17 In order to build this empathic, action-recognizing system, I created
18 a program called =CORTEX=, which is a complete platform for embodied 18 a program called =CORTEX=, which is a complete platform for embodied
19 AI research. It provides multiple senses for simulated creatures, 19 AI research. It provides multiple senses for simulated creatures,
20 including vision, touch, proprioception, muscle tension, and hearing. 20 including vision, touch, proprioception, muscle tension, and hearing.