Difference between revisions of "Pooling / Sub-sampling: Max, Mean"
| Line 4: | Line 4: | ||
* [[Dimensional Reduction Algorithms]] | * [[Dimensional Reduction Algorithms]] | ||
* [[(Deep) Convolutional Neural Network (DCNN/CNN)]] | * [[(Deep) Convolutional Neural Network (DCNN/CNN)]] | ||
| + | |||
| + | [http://ujjwalkarn.me/2016/08/11/intuitive-explanation-convnets/ Spatial Pooling (also called subsampling or downsampling) reduces the dimensionality of each feature map but retains the most important information. Spatial Pooling can be of different types: Max, Average, Sum etc. In case of Max Pooling, we define a spatial neighborhood (for example, a 2×2 window) and take the largest element from the rectified feature map within that window. Instead of taking the largest element we could also take the average (Average Pooling) or sum of all elements in that window. In practice, Max Pooling has been shown to work better. | ujjwalkarn] | ||
| + | |||
<youtube>8oOgPUO-TBY</youtube> | <youtube>8oOgPUO-TBY</youtube> | ||
Revision as of 22:28, 9 December 2018
Max Pooling
