10 lecture_dec2

10 lecture_dec2 - Final 56 multiple choice question 28 assertion/reason question 7 on student presentations Integer addition in neural networks BP

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
Final: 56 multiple choice question – 28 assertion/reason question. 7 on student presentations. Integer addition in neural networks BP not good for non-linear problems Cc minimized moving target effect Can neural net learn to add two numbers? o Encode the problem into binary (base 2) o Training rules consist of all combinations of a, b that add up to 31 o Cc faster Adding numbers in nonlinear in base 2 o 00001+00010=… no linear relation Presentation 2: Learning representation in a gated prefrontal correct model of dynamic task switching (rougier et. Al)??????? MAYBE GO OVER THE PAPER goal to create biologically based model for task switching. Want to mimic preservation errors in patients with PFC lesions task switching model – tested model on Wisconsin card sorting task o stimulus input units o hidden layer represents posterior cortex and maps input representing model’s answer o pfc context layer – biases hidden layer PFC model did better than BP and cc
Background image of page 1

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

View Full DocumentRight Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 02/14/2011 for the course PSYC 532 taught by Professor Shultz during the Fall '10 term at McGill.

Page1 / 2

10 lecture_dec2 - Final 56 multiple choice question 28 assertion/reason question 7 on student presentations Integer addition in neural networks BP

This preview shows document pages 1 - 2. Sign up to view the full document.

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