Differences
This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision | ||
courses:rg:2012:distributed-perceptron [2012/12/16 23:40] machacek |
courses:rg:2012:distributed-perceptron [2012/12/16 23:44] (current) machacek |
||
---|---|---|---|
Line 22: | Line 22: | ||
=== 4.1 Parameter Mixing === | === 4.1 Parameter Mixing === | ||
+ | |||
+ | * First attempt to map-reduce algorithm | ||
+ | * Divide the training data into shards | ||
+ | * In MAP step, train a perceptron on each shard | ||
+ | * In REDUCE step, average the trained weight vectors | ||
=== 4.2 Iterative Parameter Mixing === | === 4.2 Iterative Parameter Mixing === |