A “slow” system controls these quantities of a “fast” system in a model proposed by Jürgen (“yur-gen”) Schmidhuber in 1991. These quantities are uniformly sampled from the range negative to positive inverse square root of input number in a technique unusually named for its developer's first name, Xavier initialization. These quantities are updated during runtime in the (*) "attention" mechanism that is central to transformer models. These quantities are the coefficients in a sum that is fed into a function like softmax or ReLU (“rel-you”). The biases or, more commonly, these quantities are updated by performing gradient descent on the loss (10[1])function through backpropagation. For 10 points, name these quantities in (10[1])a neural network that represent the connection strength between neurons. ■END■