This paper revisits the special type of a neural network known under two names. In the statistics and machine learning community it is known as a multi-class logistic regression neural network. In the neural network community, it is simply the soft-max layer. The importance is underscored by its role in deep learning: as the last layer, whose autput is actually the classification of the input patterns, such as images. Our exposition focuses on mathematically rigorous derivation of the key equation expressing the gradient. The fringe benefit of our approach is a fully vectorized expression, which is a basis of an efficient implementation. The second result of this paper is the positivity of the second derivative of the cross-entropy loss function as function of the weights. This result proves that optimization methods based on convexity may be used to train this network. As a corollary, we demonstrate that no $L^2$-regularizer is needed to guarantee convergence of gradient descent.
翻译:本文重新审视了在两个名称下已知的神经网络的特殊类型。 在统计和机器学习界中, 它被称为多级物流回归神经网络。 在神经网络界中, 它只是软负层。 它的重要性通过它在深层学习中的作用而得到强调: 作为最后一个层, 其自算法实际上是输入模式的分类, 如图像。 我们的演示侧重于以数学严格的方式推断表达梯度的关键方程。 我们的方法的边际效益是一种完全传导的表达方式, 这是高效实施的基础。 本文的第二个结果是, 跨热带损失函数的第二个衍生物作为重量的函数的假设性。 这个结果证明, 可以利用基于共性的最佳方法来训练这个网络。 作为必然结果, 我们证明不需要$L$2$- 正规化器来保证梯度的归并。