 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
|
|
How to compress document count vectors
|
|
|
|
|
|
|
|
2000
reconstructed counts
|
|
|
|
|
|
|
|
 |
|
|
|
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
• |
We train the
|
|
|
autoencoder to
|
|
|
reproduce its
input
|
|
|
vector as its
output
|
|
|
• |
This forces it to
|
|
|
compress as much
|
|
|
information as
possible
|
|
|
into the 2 real
numbers
|
|
|
in the central
bottleneck.
|
|
• |
These 2 numbers
are
|
|
|
then a good way
to
|
|
|
visualize
documents.
|
|
|
|
|
|
|
|
|
|
|
 |
|
|
|
|
|
|
|
|
|
|
|
 |
|
|
|
|
|
|
|
|
|
|
|
 |
|
|
|
|
|
|
|
|
|
|
|
 |
|
|
|
|
|
|
|
|
|
|
|
|
 |
|
|
|
 |
Input
vector uses
|
Poisson
units
|
|
|
|
|
|
|
|
|
|
|
|
|