The key idea is to first break the rote memories by network pruning to address memorization overfitting in the inner loop, and then the gradients of pruned sub-networks naturally form the high-quality augmentation of the meta-gradient to alleviate learner overfitting in the outer loop.
Adversarial robustness is a key concept in measuring the ability of neural networks to defend against adversarial attacks during the inference phase.
To overcome them, we propose a novel bi-level-optimization-based multi-view learning framework, where the representation is learned in a uniform-to-specific manner.
To this end, we propose a novel framework called stochastic noise-tolerated supervised contrastive learning (SNSCL) that confronts label noise by encouraging distinguishable representation.
In this paper, we explore the potential of self-training via additional unlabeled data for mitigating backdoor attacks.
The advances in deep learning (DL) techniques have the potential to deliver transformative technological breakthroughs to numerous complex tasks in modern power systems that suffer from increasing uncertainty and nonlinearity.
LDC is built upon a parameterized calibration unit (PCU), which initializes biased distributions for all classes based on classifier vectors (memory-free) and a single covariance matrix.
Deep learning-based Multi-Task Classification (MTC) is widely used in applications like facial attributes and healthcare that warrant strong privacy guarantees.
Deep learning-based Multi-Task Classification (MTC) is widely used in applications like facial attribute and healthcare that warrant strong privacy guarantees.
In this paper, we propose a method to estimate not only a depth map but an AiF image from a set of images with different focus positions (known as a focal stack).
K-Nearest Neighbor (kNN)-based deep learning methods have been applied to many applications due to their simplicity and geometric interpretability.
This immuno-mimetic model leads to a new computational biology framework for robustification of deep neural networks against adversarial attacks.
Initializing a population of exemplars that is balanced across classes, RAILS starts from a uniform label distribution that encourages diversity and uses an evolutionary optimization process to adaptively adjust the predictive label distribution in a manner that emulates the way the natural immune system recognizes novel pathogens.
Despite the generalization power of the meta-model, it remains elusive that how adversarial robustness can be maintained by MAML in few-shot learning.
RAILS incorporates an Adaptive Immune System Emulation (AISE), which emulates in silico the biological mechanisms that are used to defend the host against attacks by pathogens.
We investigate the problem when the tensor functor by a bimodule yields a singular equivalence.
Representation Theory Rings and Algebras 18G80, 16E45, 16D20, 16G20
When the training data are maliciously tampered, the predictions of the acquired deep neural network (DNN) can be manipulated by an adversary known as the Trojan attack (or poisoning backdoor attack).
In this paper, we argue that besides CPU cores, high-speed network I/O is also important for LLC management.
Hardware Architecture Operating Systems
Recent events have led to a burgeoning awareness on the misuse of social media sites to affect political events, sway public opinion, and confuse the voters.