Multi-layer perceptron (MLP) is a fundamental component of deep learning...
Gradient regularization (GR) is a method that penalizes the gradient nor...
Free Probability Theory (FPT) provides rich knowledge for handling
mathe...
The interpretability of neural networks (NNs) is a challenging but essen...
Selective forgetting or removing information from deep neural networks (...
The Fisher information matrix (FIM) is fundamental for understanding the...
Free probability theory helps us to understand Jacobian spectrum of deep...
We investigate parameter identifiability of spectral distributions of ra...
Based on free probability theory and stochastic optimization, we introdu...
We introduce a new method to qualify the goodness of fit parameter estim...