I'm trying to understand this notation:
Specifically, what does the summation compute at each iteration? Looks like for each training sample, I compute the error (difference between target and output for that sample) and multiple that by each term in that same sample. Is this a nested summation?
// Samples [ [1, 2, 3], [4, 5, 6], ] // Predicted output [ , , ] // Target output [ , , ]
What does that summation expand into?