A novel multi-scale loss function for classification problems in machine learning
A novel multi-scale loss function for classification problems in machine learning
复制标题
DOI：
10.1016/j.jcp.2023.112679
复制
发表时间：
2021-06
期刊：
影响因子：
--
通讯作者：
L. Berlyand;Robert Creese;P. Jabin
中科院分区：
文献类型：
--
作者：
L. Berlyand;Robert Creese;P. Jabin
我们引入了双尺度损失函数，用于通过深度神经网络应用于分类问题的各种梯度下降算法。这种新方法是通用的，因为它可以应用于广泛的机器学习架构，例如从深度神经网络到支持向量机。这些双尺度损失函数允许将训练集中在训练集中未被很好分类的对象上。这导致在MNIST、CIFAR10和CIFAR100数据集上对传统深度神经网络进行测试时，适当定义的双尺度损失函数相对于更经典的交叉熵的几个性能指标有所增加。
We introduce two-scale loss functions for use in various gradient descent algorithms applied to classification problems via deep neural networks. This new method is generic in the sense that it can be applied to a wide range of machine learning architectures, from deep neural networks to support vector machines for example. These two-scale loss functions allow to focus the training onto objects in the training set which are not well classified. This leads to an increase in several measures of performance for appropriately-defined two-scale loss functions with respect to the more classical cross-entropy when tested on traditional deep neural networks on the MNIST, CIFAR10, and CIFAR100 data-sets.