The learning slowdown problem: We'v

The learning slowdown problem: We've now built upconsiderable familiarity with softmax layers of neurons. But we haven'tyet seen how a softmax layer lets us address the learning slowdown problem. To understand that, let's define the log-likelihood cost function. We'll use to denote a training input to the network, and y to denote the corresponding desired output. Then the log-likelihood cost associated to this training input isC=-Inaf.