Zobrazeno 1 - 10
of 6 986
pro vyhledávání: '"Murray , Michael"'
Autor:
Kent, Jonathan S., Murray, Michael M.
This work proposes a methodology for determining the maximum dependency length of a recurrent neural network (RNN), and then studies the effects of architectural changes, including the number and neuron count of layers, on the maximum dependency leng
Externí odkaz:
http://arxiv.org/abs/2408.11946
Bounds on the smallest eigenvalue of the neural tangent kernel (NTK) are a key ingredient in the analysis of neural network optimization and memorization. However, existing results require distributional assumptions on the data and are limited to a h
Externí odkaz:
http://arxiv.org/abs/2405.14630
The problem of benign overfitting asks whether it is possible for a model to perfectly fit noisy training data and still generalize well. We study benign overfitting in two-layer leaky ReLU networks trained with the hinge loss on a binary classificat
Externí odkaz:
http://arxiv.org/abs/2403.06903
We study benign overfitting in two-layer ReLU networks trained using gradient descent and hinge loss on noisy data for binary classification. In particular, we consider linearly separable data for which a relatively small proportion of labels are cor
Externí odkaz:
http://arxiv.org/abs/2306.09955
We study the loss landscape of both shallow and deep, mildly overparameterized ReLU neural networks on a generic finite input dataset for the squared error loss. We show both by count and volume that most activation patterns correspond to parameter r
Externí odkaz:
http://arxiv.org/abs/2305.19510