lec6.schema.web.v2

lec6.schema.web.v2 - Lecture 6 Long-Term Memory, Schemas,...

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon
1 Lecture 6 – Long-Term Memory, Schemas, and Models 2 When I was younger I could remember anything, whether it happened or not. --Mark Twain 3 How to model memory ACT-R, Anderson, CMU See http://rumpole.psych.purdue.edu/models /index.html http://www2.psy.uq.edu.au/CogPsych/Noetica/ OpenForumIssue6/introduction.html 4 ACT Theory Propositions Smallest units that can be T or F Flower Is Pretty Agent Relation 5 ACT Theory Type-token distinction Type is category X Is Blue Agent Relation Flower Is-a 6 ACT Theory, continued Activation spreads through network Learn The lawyer paid the barber The dentist fought the janitor The lawyer fought the doctor Test 1. The barber fought the dentist new 2. The lawyer paid the barber old [2 – 1] Fan Effect More links, the slower the response
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
7 Parallel Distributed Processing Representation is distributed over fixed set of nodes and links (+1 –1 –1 +1) -> (-1 –1 +1 +1) 0+0-.5-.5=-1 +1 -1 -1 +1 8 IN1 OUT1        ) 1 1 1 1 ( 0 1 ) 0 1 .( 5 . 1 5 . 1 5 . 1 ) 5 . 1 .( 0 1 0 1 0 1 ) 0 1 ( 5 . 1 5 . 1 5 . 1 ) 5 . 1 ( 0 1 0 1 0 5 . 0 5 . 0 5 . 0 5 . 5 . 0 5 . 0 5 . 0 5 . 0 ) 1 1 1 1 ( 9 IN2 OUT2 (-1 +1 –1 +1) x weights = (-1 +1 +1 –1) Knowledge does not reside in any one link, but is distributed across the weights The same weights can encode multiple bits of knowledge 10 11 Results Pairs INPUT OUTPUT PAIR3 (+1 +1 +1 –1) (+1 +1 +1 +1) PAIR1 (+1 –1 –1 +1) (-1 –1.5 +66 +.5) instead of (-1 –1 +1 +1) PAIR2 (-1 +1 –1 +1) (-1 +.5 +66 -1.5) instead of (-1 +1 +1 –1) As PAIR3 is not orthogonal to other two pairs. PAIR1 and PAIR2 are orthogonal. 12 Orthogonal Vectors In the 2-D shown in Fig 6.13, Vector h and f are orthogonal, while f and g point in similar directions Vectors f and g should be used for similar concepts (dog and cat) Vectors f and h can be used for independent concepts (dog and snake) Input: Animal
Background image of page 2
Image of page 3
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 4

lec6.schema.web.v2 - Lecture 6 Long-Term Memory, Schemas,...

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online