An Empirical and Theoretical Analysis of the Role of Depth in Convolutional Neural Networks

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...

Full description

Bibliographic Details
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

A layer-wise theoretical framework for deep learning of convolutional neural networks
by: Nguyen, Huu-Thiet, et al.
Published: (2022)

Understanding convolutional neural networks
by: Fong, R
Published: (2020)

3D convolutional neural networks for efficient and robust hand pose estimation from single depth images
by: Ge, Liuhao, et al.
Published: (2019)

Convolutional neural networks with dynamic regularization
by: Wang, Yi, et al.
Published: (2022)

Modular learning of convolutional neural networks
by: Wang, Jinhua
Published: (2023)

An energy-efficient convolution unit for depthwise separable convolutional neural networks
by: Chong, Yi Sheng, et al.
Published: (2021)

Deep convolutional neural networks for manufactured IC image analysis
by: Tan, Weiwei
Published: (2019)

CoordGate: efficiently computing spatially-varying convolutions in convolutional neural networks
by: Howard, S, et al.
Published: (2023)

Convolutional neural networks for food calorie estimation
by: Leona Ramy
Published: (2022)

A lightweight convolutional neural network for KWS
by: Wang, Yumengmeng
Published: (2022)

Emotion Recognition in Horses with Convolutional Neural Networks
by: Corujo, Luis A., et al.
Published: (2021)

Greedy layerwise training of convolutional neural networks
by: Trinh, Loc Quang.
Published: (2019)

Deterministic binary filters for convolutional neural networks
by: Tseng, V, et al.
Published: (2018)

A convolutional neural network for modelling sentences
by: Kalchbrenner, N, et al.
Published: (2014)

Recurrent Convolutional Neural Networks for Discourse Compositionality
by: Kalchbrenner, N, et al.
Published: (2013)

Visual search using convolutional neural networks
by: Ng, Sue Shen
Published: (2018)

Convolutional neural network for hyperspectral image classification
by: Yuan, Nanqi
Published: (2016)

Accelerator of convolution neural networks based on FPGA
by: Yu, Guohao
Published: (2017)

Low power convolutional neural network (CNN)
by: Lim, Wu Cong
Published: (2019)

Graph convolutional neural networks for text categorization
by: Lakhotia, Suyash
Published: (2018)

Scene classification based on convolutional neural network
by: Zou, Bojing
Published: (2018)

Implementation of a convolutional neural network on FPGA
by: Xue, Can
Published: (2018)

Object detection via convolutional neural network
by: Ong, Wee Hong
Published: (2018)

Fast convolutional neural network for image classification
by: Jeon, Young Seok
Published: (2017)

Image denoising using convolutional neural network
by: Yang, Yaqian
Published: (2018)

A Convolutional Neural Network for Modelling Sentences
by: Kalchbrenner, N, et al.
Published: (2014)

Reading text in the wild with convolutional neural networks
by: Jaderberg, M, et al.
Published: (2014)

Reading text in the wild with convolutional neural networks
by: Jaderberg, M, et al.
Published: (2015)

Leaf condition analysis using convolutional neural network and vision transformer
by: Yong, Wai Chun, et al.
Published: (2024)

Calf posture recognition using convolutional neural network
by: Tung, Tan Chen, et al.
Published: (2022)

Python extension for a convolution neural network accelerator
by: Pattanapong Khaopaibul Wu Jing Han
Published: (2022)

Understanding of Convolutional Neural Network (CNN): A Review
by: Purwono, Purwono, et al.
Published: (2022)

All-optical computing based on convolutional neural networks
by: Liao, Kun, et al.
Published: (2022)

Accelerating convolutional neural networks through enhanced designs
by: Gennari do Nascimento, M
Published: (2022)

Image Splicing Detection With Constrained Convolutional Neural Network
by: Lee, Yang Yang
Published: (2019)

Handwritten character recognition using convolutional neural network
by: Khandokar, I., et al.
Published: (2021)

Review of deep convolution neural network in image classification
by: Al-Saffar, Ahmed Ali Mohammed, et al.
Published: (2017)

Visualizing and interpreting convolutional neural networks on genomic data
by: Liu, Ge, Ph. D. Massachusetts Institute of Technology
Published: (2018)

Enhancing Evolutionary Couplings with Deep Convolutional Neural Networks
by: Liu, Yang, et al.
Published: (2018)

Development of a learning system for convolutional neural network
by: Liu, Hang
Published: (2020)