The Influence Eliminating Unlearning framework maximizes relearning convergence delay via weight decay and noise injection to remove the influence of a forgetting set while preserving accuracy on retained data.
On weight initialization in deep neural networks
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
A proper initialization of the weights in a neural network is critical to its convergence. Current insights into weight initialization come primarily from linear activation functions. In this paper, I develop a theory for weight initializations with non-linear activations. First, I derive a general weight initialization strategy for any neural network using activation functions differentiable at 0. Next, I derive the weight initialization strategy for the Rectified Linear Unit (RELU), and provide theoretical insights into why the Xavier initialization is a poor choice with RELU activations. My analysis provides a clear demonstration of the role of non-linearities in determining the proper weight initializations.
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
Proposes a modular unified lightweight neural architecture for demosaicing multiple pixel-bin CFAs together with a learning-free CFA identification module.
Standard PINNs fail to recover layer moduli in multilayer pavement systems due to domain discontinuities; XPINN improves but remains sensitive to weighting and noise; DiffFEM yields superior accuracy, stability, and efficiency on the same synthetic benchmark.
Derives lower bound on gradient variance and probabilistic concentration bounds for Gaussian-initialized IQP QCBMs trained via MMD loss.
Presents a non-distortive cancelable face template method via targeted image distortion that maintains identity signals for neural embedding models on MNIST and LFW data.
citing papers explorer
-
Efficient Unlearning through Maximizing Relearning Convergence Delay
The Influence Eliminating Unlearning framework maximizes relearning convergence delay via weight decay and noise injection to remove the influence of a forgetting set while preserving accuracy on retained data.
-
An Extensible and Lightweight Unified Architecture for Demosaicing Pixel-bin Image Sensors
Proposes a modular unified lightweight neural architecture for demosaicing multiple pixel-bin CFAs together with a learning-free CFA identification module.
-
Critical evaluation of PINN for FWD inverse analysis and differentiable FEM as an alternative
Standard PINNs fail to recover layer moduli in multilayer pavement systems due to domain discontinuities; XPINN improves but remains sensitive to weighting and noise; DiffFEM yields superior accuracy, stability, and efficiency on the same synthetic benchmark.
-
Trainability of IQP Quantum Circuit Born Machines Under Gaussian Initialization
Derives lower bound on gradient variance and probabilistic concentration bounds for Gaussian-initialized IQP QCBMs trained via MMD loss.
-
Embedding Non-Distortive Cancelable Face Template Generation
Presents a non-distortive cancelable face template method via targeted image distortion that maintains identity signals for neural embedding models on MNIST and LFW data.