In this paper, we consider the problem of iterative machine teaching, where a teacher provides examples sequentially based on the current iterative learner.

Deep learning classifiers are assisting humans in making decisions and hence the user's trust in these models is of paramount importance. Trust is often a function of constant behavior.

Machine learning advances in the last decade have relied significantly on large-scale datasets that continue to grow in size. Increasingly, those datasets also contain different data modalities.

On-device training enables the model to adapt to new data collected from the sensors by fine-tuning a pre-trained model.

We study deep neural networks (DNNs) trained on natural image data with entirely random labels.

Understanding to what extent neural networks memorize training data is an intriguing question with practical and theoretical implications.

We propose Nouveau V AE (NV AE), a deep hierarchical V AE built for image generation using depth-wise separable convolutions and batch normalization.