Name
Abstract | ||
|---|---|---|
The classical bias variance trade-off cannot accurately explain how over-parameterized Deep Neural Networks (DNNs) avoid overfitting and achieve good generalization. To address the problem, we alternatively derive a Mutual Information (MI) trade-off based on the recently proposed MI explanation for generalization. In addition, we propose a probabilistic representation of DNNs for accurately estima... |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1109/MLSP52302.2021.9596544 | 2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) |
Keywords | DocType | ISSN |
Deep learning,Conferences,Signal processing,Probabilistic logic,Mutual information | Conference | 2161-0363 |
ISBN | Citations | PageRank |
978-1-7281-6338-3 | 0 | 0.34 |
References | Authors | |
0 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xinjie Lan | 1 | 1 | 1.70 |
| Bin B. Zhu | 2 | 22 | 10.46 |
| charles g boncelet | 3 | 27 | 10.06 |
| Kenneth E. Barner | 4 | 812 | 70.19 |