It is used to perform max pooling operations on temporal data. The signature of the MaxPooling1D function and its arguments with default value is as follows −
keras.layers.MaxPooling1D ( pool_size = 2, strides = None, padding = 'valid', data_format = 'channels_last' )
pool_size refers the max pooling windows.
strides refer the factors for downscale.
Similarly, MaxPooling2D and MaxPooling3D are used for Max pooling operations for spatial data.