Please someone elaborate What’s the Difference Between Strided Convolution and Pooling?
Strided convolution is a type of operation that is used in deep learning to reduce the size of an input tensor by moving a kernel (a small matrix of weights) across the tensor and applying it to the values in the tensor. The kernel is moved in steps, called the “stride”, and the size of the overlap between the kernel and the tensor determines the size of the output tensor.
Pooling is another technique that is used in deep learning to reduce the size of an input tensor. It works by looking at small neighborhoods of values within the tensor and aggregating them in some way, such as by taking the maximum or average value. Pooling can help make a model more robust to small translations in the input data and can also reduce the number of parameters in the model.