Difference between revisions of "Class meeting for 10-605 Parallel Perceptrons 2"
From Cohen Courses
Jump to navigationJump to search (→Slides) |
|||
Line 18: | Line 18: | ||
=== Optional Readings === | === Optional Readings === | ||
* [http://www.cs.cmu.edu/~wcohen/10-707/vp-notes/vp.pdf Notes on voted perceptron.] | * [http://www.cs.cmu.edu/~wcohen/10-707/vp-notes/vp.pdf Notes on voted perceptron.] | ||
+ | |||
+ | === What you should remember === | ||
+ | |||
+ | * The averaged perceptron and the voted perceptron | ||
+ | * Approaches to parallelizing perceptrons (and other on-line learning methods, like SGD) | ||
+ | ** Parameter mixing | ||
+ | ** Iterative parameter mixing (IPM) | ||
+ | * The meaning and implications of the theorems give for convergence of the basic perceptron and the IPM version |
Revision as of 10:16, 16 October 2015
This is one of the class meetings on the schedule for the course Machine Learning with Large Datasets 10-605 in Fall_2015.
Slides
Perceptrons, continued:
Parallel perceptrons with iterative parameter mixing:
Readings for the Class
- Distributed Training Strategies for the Structured Perceptron, R. McDonald, K. Hall and G. Mann, North American Association for Computational Linguistics (NAACL), 2010.
Optional Readings
What you should remember
- The averaged perceptron and the voted perceptron
- Approaches to parallelizing perceptrons (and other on-line learning methods, like SGD)
- Parameter mixing
- Iterative parameter mixing (IPM)
- The meaning and implications of the theorems give for convergence of the basic perceptron and the IPM version