Professional Documents
Culture Documents
Forrester System Dynamics - Lecture
Forrester System Dynamics - Lecture
hv@cs.mcgill.ca
1/20
Methodology
1. levels/stocks and rates/ows
dP dt
Level population inventory money
BR
DR
Outow death rate sales expenses
birth rate
birth
population
hv@cs.mcgill.ca
2/20
Causal Relationships
graduates
SOL
graduates
latent variable
SOL
hv@cs.mcgill.ca
3/20
Archetypes
Bellinger http://www.outsights.com/systems/
hv@cs.mcgill.ca
4/20
hv@cs.mcgill.ca
5/20
hv@cs.mcgill.ca
6/20
Archetypes: Escalation
hv@cs.mcgill.ca
7/20
hv@cs.mcgill.ca
8/20
hv@cs.mcgill.ca
9/20
hv@cs.mcgill.ca
10/20
prey_surplus_BR
predator_surplus_DR
Predator
Prey
hv@cs.mcgill.ca
11/20
BR = f (POP, POL, MSL, ...) BR = BRN.f1(POP, POL, MSL, ...) BR = BRN.POP.f2(POL, MSL, ...) BR = BRN.POP.f3(POL).f4(MSL). ... f3(POL) = "inversely proportional" f4(MSL) = "proportional"
hv@cs.mcgill.ca
12/20
hv@cs.mcgill.ca
13/20
Feature Extraction
1. Measurement data and model candidates 2. Structure selection and validation 3. Parameter estimation 4. Model use
hv@cs.mcgill.ca
14/20
Feature Rationale
hv@cs.mcgill.ca
15/20
Throwing Stones
Candidate Models
1. x 2. x
1 2 2 gt
v0t
Asin bt
hv@cs.mcgill.ca
16/20
hv@cs.mcgill.ca
F2
200
hv@cs.mcgill.ca
bA bA
bB bB
1 tg bt b
F1
gA gB
xi xi
gi
2xi ti2
2xi i ti
AB
17/20
18/20
2 Feature t
hv@cs.mcgill.ca
19/20
Pandemomium Model
edge
vector templates
CCD
vectorise
stroke tracing
threshold smooth thin background neural net strokes convex deficiences voting scheme
pixels
"image" demon
"feature" demon
"cognitive" demon
"decision" demon
hv@cs.mcgill.ca
20/20