> I generally wouldn't define algorithm as such, although I can see where the lines between them can become blurry.
Its pretty clear cut tbh. An algorithm is a set of steps to follow to produce some output. A trained model is, 'hey do these matrix multiplications with these coefficients to get an output'. The fact that the exact coefficients were arrived at via backprop, doesn't make it not an algorithm.
Its pretty clear cut tbh. An algorithm is a set of steps to follow to produce some output. A trained model is, 'hey do these matrix multiplications with these coefficients to get an output'. The fact that the exact coefficients were arrived at via backprop, doesn't make it not an algorithm.