CNNComparator: Comparative Analytics of Convolutional Neural Networks
This addresses the problem for machine learning practitioners who need to interpret CNN training dynamics, though it is incremental as it builds on existing visualization methods.
The paper tackles the challenge of understanding how learned parameters relate to performance in convolutional neural networks (CNNs) during training, by presenting a visual analytics approach that compares snapshots of a CNN model at different epochs to provide insights for better model design or training.
Convolutional neural networks (CNNs) are widely used in many image recognition tasks due to their extraordinary performance. However, training a good CNN model can still be a challenging task. In a training process, a CNN model typically learns a large number of parameters over time, which usually results in different performance. Often, it is difficult to explore the relationships between the learned parameters and the model performance due to a large number of parameters and different random initializations. In this paper, we present a visual analytics approach to compare two different snapshots of a trained CNN model taken after different numbers of epochs, so as to provide some insight into the design or the training of a better CNN model. Our system compares snapshots by exploring the differences in operation parameters and the corresponding blob data at different levels. A case study has been conducted to demonstrate the effectiveness of our system.