An Empirical and Theoretical Analysis of the Role of Depth in Convolutional Neural Networks
While over-parameterized neural networks are capable of perfectly fitting (interpolating) training data, these networks often perform well on test data, thereby contradicting classical learning theory. Recent work provided an explanation for this phenomenon by introducing the double descent curve, s...
Main Author: | Nichani, Eshaan |
---|---|
Other Authors: | Uhler, Caroline |
Format: | Thesis |
Published: |
Massachusetts Institute of Technology
2022
|
Online Access: | https://hdl.handle.net/1721.1/139174 |
Similar Items
-
An in-depth analysis of Convolutional Neural Network architectures with transfer learning for skin disease diagnosis
by: Rifat Sadik, et al.
Published: (2023-11-01) -
Empirical analysis of multiple modalities for emotion recognition using convolutional neural network
by: Ram Avtar Jaswal, et al.
Published: (2023-04-01) -
Classification of Water Turbidity and Depth of Secchi Disk using Convolutional Neural Network
by: Hajar Feizi, et al.
Published: (2023-06-01) -
Object Detection and Depth Estimation Approach Based on Deep Convolutional Neural Networks
by: Huai-Mu Wang, et al.
Published: (2021-07-01) -
Depth Evaluation of Tiny Defects on or near Surface Based on Convolutional Neural Network
by: Qinnan Fei, et al.
Published: (2023-10-01)