Doc(Language.ANY, DocScope.ALL){
            """
                Applies the softmax activation function to the input, then implement multi-class cross entropy:<br>
                {@code -sum_classes label[i] * log(p[c])} where {@code p = softmax(logits)}<br>
                If LossReduce#NONE is used, returned shape is [numExamples] out for [numExamples, numClasses] predicitons/labels;