Deep Learning
StateMask: Explaining Deep Reinforcement Learning through State Mask
Most existing methods explain why an agent takes individual actions rather than pinpointing the critical steps to its final reward.
Andrey Kuzmin, Markus Nagel, Mart van Baalen, Arash Behboodi, Tijmen Blankevoort Qualcomm AI Research
In this paper, we set out to answer the question on which is better: neural network quantization or pruning? By answering this question, we hope to inform design decisions made on neural network hardware going forward. We provide an extensive comparison between the two techniques for compressing deep neural networks.
Interpreting Unsupervised Anomaly Detection in Security via Rule Extraction Ruoyu Li, Qing Li, Yu Zhang
Compared to supervised methods, this type of method is more desirable in security domains as 1) it hardly requires labeled attack/malicious data during the training (i.e., zero-positive
