Uncertainty Estimation Using Variational Mixture of Gaussians Capsule Network for Health Image Classification

<div>Training/validation accuracy/loss curves for the proposed model. The model learns and converges on (b) Fashion-MNIST and (c) MNIST as early as epoch 30. Learning takes time for (a) CIFAR-10 and (d) COVID-19 Radiography images but achieves convergence at epoch 90. We notice that the model converges faster for the images that are less complex compared to CIFAR-10 and COVID-19.</div>

Computational Intelligence and Neuroscience

fig2

Figure 2

Figure 2: Uncertainty Estimation Using Variational Mixture of Gaussians Capsule Network for Health Image Classification 