Pooling

From Ufldl

Jump to: navigation, search
(Pooling: Overview)
 
Line 13: Line 13:
If one chooses the pooling regions to be contiguous areas in the image and only pools features generated from the same (replicated) hidden units. Then, these pooling units will then be '''translation invariant'''. This means that the same (pooled) feature will be active even when the image undergoes (small) translations. Translation-invariant features are often desirable; in many tasks (e.g., object detection, audio recognition), the label of the example (image) is the same even when the image is translated. For example,  if you were to take an MNIST digit and translate it left or right, you would want your classifier to still accurately classify it as the same digit regardless of its final position.
If one chooses the pooling regions to be contiguous areas in the image and only pools features generated from the same (replicated) hidden units. Then, these pooling units will then be '''translation invariant'''. This means that the same (pooled) feature will be active even when the image undergoes (small) translations. Translation-invariant features are often desirable; in many tasks (e.g., object detection, audio recognition), the label of the example (image) is the same even when the image is translated. For example,  if you were to take an MNIST digit and translate it left or right, you would want your classifier to still accurately classify it as the same digit regardless of its final position.
-
== Notes ==
+
== Formal description ==
-
Formally, after obtaining our convolved features as earlier, we decide the size of the region, say <math>m \times n</math> to pool our convolved features over. Then, we divide our convolved features into disjoint <math>m \times n</math> regions, and take the maximum (or mean) feature activation over these regions to obtain the pooled convolved features. These pooled features can then be used for classification.
+
Formally, after obtaining our convolved features as described earlier, we decide the size of the region, say <math>m \times n</math> to pool our convolved features over. Then, we divide our convolved features into disjoint <math>m \times n</math> regions, and take the mean (or maximum) feature activation over these regions to obtain the pooled convolved features. These pooled features can then be used for classification.
 +
 
 +
 
 +
 
 +
{{Languages|池化|中文}}

Latest revision as of 04:17, 8 April 2013

Personal tools