Difference between revisions of "Pooling / Sub-sampling: Max, Mean"
| (4 intermediate revisions by the same user not shown) | |||
| Line 1: | Line 1: | ||
| + | {{#seo: | ||
| + | |title=PRIMO.ai | ||
| + | |titlemode=append | ||
| + | |keywords=artificial, intelligence, machine, learning, models, algorithms, data, singularity, moonshot, Tensorflow, Google, Nvidia, Microsoft, Azure, Amazon, AWS | ||
| + | |description=Helpful resources for your journey with artificial intelligence; videos, articles, techniques, courses, profiles, and tools | ||
| + | }} | ||
[http://www.youtube.com/results?search_query=max+mean+pooling+sub-sampling+deep+learning YouTube search...] | [http://www.youtube.com/results?search_query=max+mean+pooling+sub-sampling+deep+learning YouTube search...] | ||
| + | [http://www.google.com/search?q=max+mean+pooling+sub-sampling+deep+learning+deep+machine+learning+ML+artificial+intelligence ...Google search] | ||
* [[Softmax]] | * [[Softmax]] | ||
| − | * [[Dimensional Reduction | + | * [[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> | ||
<youtube>I-JKxcpbRT4</youtube> | <youtube>I-JKxcpbRT4</youtube> | ||
<youtube>YFoOhmNZiSw</youtube> | <youtube>YFoOhmNZiSw</youtube> | ||
| − | <youtube> | + | <youtube>qzK7FSyZUxI</youtube> |
== Max Pooling == | == Max Pooling == | ||
| Line 14: | Line 24: | ||
<youtube>ZjM_XQa5s6s</youtube> | <youtube>ZjM_XQa5s6s</youtube> | ||
| + | <youtube>2-75C-yZaoA</youtube> | ||
| + | <youtube>s2DwiwrR1qU</youtube> | ||
| + | <youtube>mW3KyFZDNIQ</youtube> | ||
Latest revision as of 20:57, 27 June 2019
YouTube search... ...Google search
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
Max Pooling
