Max pooling block 1D
The 1D Max pooling block reduces the size of the data, the number of parameters, the amount of computation needed, and it also controls overfitting.
How does max pooling work?
The 1D max pooling block moves a pool (window) of a set size over the incoming data with a set stride, computing the maximum in each specific window.
When to use max pooling 1D
Max pooling layers are inserted after one or more convolutional layers; they help inner convolutional layers receive information from a bigger portion of the original vector If we see convolutional layers as detectors of a specific feature, max pooling keeps only the “strongest” value of that feature inside the pooling rectangle. Each channel (hence each feature) is treated separately.
Horizontal pool: The size of the vector within which the maximum is computed. Default: 2
Horizontal stride: The number of cells to move while performing the pooling along the vector. Default: 1
Padding: Same results in padding the input such that the output has the same length as the original input. Valid means "no padding".