31
Finding binary codes for documents
 2000  reconstructed counts
• Train an auto-encoder using 30
logistic units for the code layer.
• During the fine-tuning stage,
add noise to the inputs to the
code units.
– The “noise” vector for each
training case is fixed. So we
still get a deterministic
gradient.
– The noise forces their
activities  to become bimodal
in order to resist the effects
of the noise.
– Then we simply round the
activities of the 30 code units
to 1 or 0.
500 neurons
250 neurons
30
noise
250 neurons
500 neurons
     2000  word counts