conftrace_

network depth

29 papers

Explore in graph

Co-occurring keywords

network width (21) neural network (6616) deep network (152) relu network (143) convolutional neural network (4226) function approximation (319) deep neural network (1803) deep learning theory (36) approximation theory (77) batch normalization (222)

Papers

On the Hardness of Training Deep Neural Networks Discretely AAAI 2025
Till the Layers Collapse: Compressing a Deep Neural Network Through the Lenses of Batch Normalization Layers. AAAI 2025
Revisiting Neural Networks for Continual Learning: An Architectural Perspective IJCAI 2024
Quasi-Equivalence between Width and Depth of Neural Networks JMLR 2023
Size and depth of monotone neural networks: interpolation and approximation NIPS 2022
DF-ResNet: Boosting Speaker Verification Performance with Depth-First Design INTERSPEECH 2022
Vanishing Curvature in Randomly Initialized Deep ReLU Networks AISTATS 2022
Neural Tangent Kernel Beyond the Infinite-Width Limit: Effects of Depth and Initialization ICML 2022
Non-deep Networks NIPS 2022
Width is Less Important than Depth in ReLU Neural Networks COLT 2022
Batch Normalization Orthogonalizes Representations in Deep Random Networks NIPS 2021
Scaling Properties of Deep Residual Networks ICML 2021
Limits to Depth Efficiencies of Self-Attention NIPS 2020
Going Deep: Graph Convolutional Ladder-Shape Networks AAAI 2020
On the Number of Linear Regions of Convolutional Neural Networks ICML 2020
Universal Approximation with Deep Narrow Networks COLT 2020
Sharp Representation Theorems for ReLU Networks with Precise Dependence on Depth NIPS 2020
Bayesian Learning of Neural Network Architectures AISTATS 2019
LIT: Learned Intermediate Representation Training for Model Compression ICML 2019
Depth Growing for Neural Machine Translation ACL 2019
The emergence of spectral universality in deep networks AISTATS 2018
Bounds on the Approximation Power of Feedforward Neural Networks ICML 2018
PolyNet: A Pursuit of Structural Diversity in Very Deep Networks CVPR 2017
On the Expressive Power of Deep Neural Networks ICML 2017
Depth-Width Tradeoffs in Approximating Natural Functions with Neural Networks ICML 2017