Cognitive Modelling Assignment 1 MODEL 6: MSc Cognitive Science Elaine Cohalan Feb 9 th 2005
Single Category Classification Stage 1:
Stage 1: Tasks: Come up with a computational model that, for each test item computes that item's degree of membership in the three categories A, B and C. Use the attributes of that test item and compare to the occurrence of those attributes in the 16 training items.
Additive Weighted Prototype Model Training Items Given:
Developing the Prototypes: Category A:
Category B:
Category C:
Applying Prototypes to Test Items:
Correlation of prototype model scores with human scores:
Category A:
Category B:
Category C:
Total Correlation:
Conjunctions Stage 2:
Stage 2: Tasks: Independent Approach to Conjunctions. Constituent Membership scores combined using function sum (A+B).
To compute an items membership in a conjunction A&B using the Independent Prototype Model, combine that item’s membership in A and its computed membership in B. Formula for sum(A+B): membership(x, A&B) = sum(A,B) = (membership(x,A) + membership(x,B))
Category A and B: Using Prototypes A and B:
Correlation with Human Score:
Category A and C: Using Prototypes A and C:
Correlation with Human Score:
Category B and C: Using Prototypes B and C:
Correlation with Human Score:
Total Correlation for Conjunctions: