Feature Hashing approach is "SGD-based classifiers avoid the need to predetermine vector size by simply picking a reasonable size and shoehorning the training data into vectors of that size" now…

Question

Options

• AIs a problem with accuracy
• BIt is hard to understand what classifier is doing
• CIt is easy to understand what classifier is doing
• DIs a problem with accuracy as well as hard to understand what classifier us doing

• A
  7% (2)
• B
  83% (25)
• C
  7% (2)
• D
  3% (1)

Explanation

SGD-based classifiers avoid the need to predetermine vector size by simply picking a reasonable size and shoehorning the training data into vectors of that size. This approach is known as feature hashing. The shoehorning is done by picking one or more locations by using a hash of the name of the variable for continuous variables or a hash of the variable name and the category name or word for categorical, textlike, or word-like data. This hashed feature approach has the distinct advantage of requiring less memory and one less pass through the training data, but it can make it much harder to reverse engineer vectors to determine which original feature mapped to a vector location. This is because multiple features may hash to the same location. With large vectors or with multiple locations per feature, this isn't a problem for accuracy but it can make it hard to understand what a classifier is doing. An additional benefit of feature hashing is that the unknown and unbounded vocabularies typical of word-like variables aren't a problem.

No community discussion yet for this question.