Search Results for author:
Found 5 papers, 0 papers with code
Towards Predictable Feature Attribution: Revisiting and Improving Guided BackPropagation
Recently, backpropagation(BP)-based feature attribution methods have been widely adopted to interpret the internal mechanisms of convolutional neural networks (CNNs), and expected to be human-understandable (lucidity) and faithful to decision-making processes (fidelity).
MMCGAN: Generative Adversarial Network with Explicit Manifold Prior
Since the basic assumption of conventional manifold learning fails in case of sparse and uneven data distribution, we introduce a new target, Minimum Manifold Coding (MMC), for manifold learning to encourage simple and unfolded manifold.
Adaptive Adversarial Logits Pairing
Specifically, AALP consists of an adaptive feature optimization module with Guided Dropout to systematically pursue fewer high-contribution features, and an adaptive sample weighting module by setting sample-specific training weights to balance between logits pairing loss and classification loss.
A Generalization Theory based on Independent and Task-Identically Distributed Assumption
The derived generalization bound based on the ITID assumption identifies the significance of hypothesis invariance in guaranteeing generalization performance.
Understanding Deep Learning Generalization by Maximum Entropy
DNN is then regarded as approximating the feature conditions with multilayer feature learning, and proved to be a recursive solution towards maximum entropy principle.
