Class Notes (806,530)
Canada (492,283)
Psychology (3,191)
PSYC 532 (11)

Connectionism Lecture Notes.docx

4 Pages
Unlock Document

McGill University
PSYC 532
Rick Schultz

Connectionism Lecture Notes These are additional notes to the slides so it would be best to follow along with the slides for full coverage of the topic…. Each Unit Has Simple Program:  Difference between biology and computer= excitatory and inhibition Psychological Equivalents:  Pattern of activation across units (active or not)  Long term v.s Short term memory  Connection weights are being adjusted  Adjustment of connection weights= in order to reduce error ~Most general scheme… Auto-Associator network:  Circles= units which are all doing the same job + fully connected to each other  Inputs-all are receiving this  Outputs-all sending this  Units + connection weights  Taking out some unit will make it do different things Other Networks Have Restrictions:  Some constraints on values of connections e.g: Some groups of units have mutually inhibitory connections (which are competing with each other) ~Good at learning patterns + generalization…  Output units= answer to problem  Hidden units= internal computation, no output or input  Input units= describe particular problem working on o No lateral connections o No communicating within a layer o No backward connections Distributed representations:  Each rectangle represents a neuron  Pattern represents a concept or an idea  Each different pattern represents a different idea  Each unit (96) is participating in different concepts  Each concept requires many units (can represent a large amount of concepts)  Local= 96  Distributed= 96 = 2 (more efficient especially in AI) Net Input To A Unit j: ~How much of an activation value is coming in..  X= Net input to a unit j  W= Amount of connection weight (w) of the unit (j)  Y= Activation (Y) sending unit (i) Spreading Activation:  Graphical version of the equation…  Integrated activation Linear Function: y=x:  Useless because it is not changing the input in a non-linear way ~Activation= average firing rate ~More inte
More Less

Related notes for PSYC 532

Log In


Don't have an account?

Join OneClass

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

Sign up

Join to view


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.