DeepAI
Log In Sign Up

Negative Log Likelihood Ratio Loss for Deep Neural Network Classification

04/27/2018
by   Donglai Zhu, et al.
0

In deep neural network, the cross-entropy loss function is commonly used for classification. Minimizing cross-entropy is equivalent to maximizing likelihood under assumptions of uniform feature and class distributions. It belongs to generative training criteria which does not directly discriminate correct class from competing classes. We propose a discriminative loss function with negative log likelihood ratio between correct and competing classes. It significantly outperforms the cross-entropy loss on the CIFAR-10 image classification task.

READ FULL TEXT

page 1

page 2

page 3

page 4

07/31/2019

Competing Ratio Loss for Discriminative Multi-class Image Classification

The development of deep convolutional neural network architecture is cri...
05/01/2019

On Expected Accuracy

We empirically investigate the (negative) expected accuracy as an altern...
03/06/2020

SimLoss: Class Similarities in Cross Entropy

One common loss function in neural network classification tasks is Categ...
12/04/2018

Set Cross Entropy: Likelihood-based Permutation Invariant Loss Function for Probability Distributions

We propose a permutation-invariant loss function designed for the neural...
06/16/2019

Mixture separability loss in a deep convolutional network for image classification

In machine learning, the cost function is crucial because it measures ho...
04/24/2019

A Novel Re-weighting Method for Connectionist Temporal Classification

The connectionist temporal classification (CTC) enables end-to-end seque...
05/01/2019

Introducing Graph Smoothness Loss for Training Deep Learning Architectures

We introduce a novel loss function for training deep learning architectu...