Class Notes (835,866)
Canada (509,453)
COGS 100 (67)
Lecture

COGS 100 Week 12 Lec 2

2 Pages
109 Views
Unlock Document

Department
Cognitive Science
Course
COGS 100
Professor
Radoslava Trnavac
Semester
Winter

Description
COGS 100 Week 12 Lec 2 Neural Networks •Information Processing: how many kinds have we talked about? Physical symbol system •How does this processing happen? Manipulate structures with syntactic rules. Close to language - has symbols, syntax and semantics •For syntax and semantics to coordinate need rules with respect both syntax and semantics? •How does Turing machine analyze data? Machine head from one cell to another cell, one step at a time •This is serial processing •1986 - Parallel processing, parallel distribution •Approach for creating comp models that rep concepts and properties based on characteristics of brain Idea of neural networks •Have units, are basically neurons •Connections between like axons -info transmitted here •Strength of connections depends on output we get when we train network? •Semantic network: based on concepts and meanings; nodes break off from base class, then relate further concepts. Used for categorization and organization. Also how we retrieve info. •Distance between concepts relates to time taken to associate things •Cognitive economy: only store everything once? Use space economically? •Problems of semantic network approach: pigs as animals before pigs as mammals •Potential solutions: •Things activated together frequently, become associated •Adjust strength of connections and distance between - essence of connectionism •Take lots of cycles to get right output? •Do the reading. Seriously. •Neural networks better at graceful degradation, PSS is more binary, if one thing breaks (one fac
More Less

Related notes for COGS 100

Log In


OR

Join OneClass

Access over 10 million pages of study
documents for 1.3 million courses.

Sign up

Join to view


OR

By registering, I agree to the Terms and Privacy Policies
Already have an account?
Just a few more details

So we can recommend you notes for your school.

Reset Password

Please enter below the email address you registered with and we will send you a link to reset your password.

Add your courses

Get notes from the top students in your class.


Submit