A Hybrid of Generative and Discriminative Models Based on the Gaussian-coupled Softmax Layer
This work addresses the challenge of integrating generative and discriminative approaches for classification tasks, but it is incremental as it builds on existing hybrid methods.
The paper tackles the problem of combining generative and discriminative models in a single neural network to leverage their respective advantages, such as using unsupervised data and achieving calibrated confidence, and demonstrates its application in semi-supervised learning and confidence calibration.
Generative models have advantageous characteristics for classification tasks such as the availability of unsupervised data and calibrated confidence, whereas discriminative models have advantages in terms of the simplicity of their model structures and learning algorithms and their ability to outperform their generative counterparts. In this paper, we propose a method to train a hybrid of discriminative and generative models in a single neural network (NN), which exhibits the characteristics of both models. The key idea is the Gaussian-coupled softmax layer, which is a fully connected layer with a softmax activation function coupled with Gaussian distributions. This layer can be embedded into an NN-based classifier and allows the classifier to estimate both the class posterior distribution and the class-conditional data distribution. We demonstrate that the proposed hybrid model can be applied to semi-supervised learning and confidence calibration.