Normalization techniques in training dnns: Methodology, analysis and application

L Huang, J Qin, Y Zhou, F Zhu, L Liu… - IEEE transactions on …, 2023 - ieeexplore.ieee.org
Normalization techniques are essential for accelerating the training and improving the
generalization of deep neural networks (DNNs), and have successfully been used in various …

Piecewise linear neural networks and deep learning

Q Tao, L Li, X Huang, X Xi, S Wang… - Nature Reviews Methods …, 2022 - nature.com
As a powerful modelling method, piecewise linear neural networks (PWLNNs) have proven
successful in various fields, most recently in deep learning. To apply PWLNN methods, both …

Weisfeiler and lehman go topological: Message passing simplicial networks

C Bodnar, F Frasca, Y Wang, N Otter… - International …, 2021 - proceedings.mlr.press
The pairwise interaction paradigm of graph machine learning has predominantly governed
the modelling of relational systems. However, graphs alone cannot capture the multi-level …

Neural architecture search on imagenet in four gpu hours: A theoretically inspired perspective

W Chen, X Gong, Z Wang - arXiv preprint arXiv:2102.11535, 2021 - arxiv.org
Neural Architecture Search (NAS) has been explosively studied to automate the discovery of
top-performer neural networks. Current works require heavy training of supernet or intensive …

Neural architecture search for spiking neural networks

Y Kim, Y Li, H Park, Y Venkatesha, P Panda - European conference on …, 2022 - Springer
Abstract Spiking Neural Networks (SNNs) have gained huge attention as a potential energy-
efficient alternative to conventional Artificial Neural Networks (ANNs) due to their inherent …

Zen-nas: A zero-shot nas for high-performance image recognition

M Lin, P Wang, Z Sun, H Chen, X Sun… - Proceedings of the …, 2021 - openaccess.thecvf.com
Accuracy predictor is a key component in Neural Architecture Search (NAS) for ranking
architectures. Building a high-quality accuracy predictor usually costs enormous …

When deep learning meets polyhedral theory: A survey

J Huchette, G Muñoz, T Serra, C Tsay - arXiv preprint arXiv:2305.00241, 2023 - arxiv.org
In the past decade, deep learning became the prevalent methodology for predictive
modeling thanks to the remarkable accuracy of deep neural networks in tasks such as …

The combinatorial brain surgeon: pruning weights that cancel one another in neural networks

X Yu, T Serra, S Ramalingam… - … Conference on Machine …, 2022 - proceedings.mlr.press
Neural networks tend to achieve better accuracy with training if they are larger {—} even if
the resulting models are overparameterized. Nevertheless, carefully removing such excess …

Automated deep learning: Neural architecture search is not the end

X Dong, DJ Kedziora, K Musial… - … and Trends® in …, 2024 - nowpublishers.com
Deep learning (DL) has proven to be a highly effective approach for developing models in
diverse contexts, including visual perception, speech recognition, and machine translation …

AZ-NAS: Assembling Zero-Cost Proxies for Network Architecture Search

J Lee, B Ham - Proceedings of the IEEE/CVF Conference …, 2024 - openaccess.thecvf.com
Training-free network architecture search (NAS) aims to discover high-performing networks
with zero-cost proxies capturing network characteristics related to the final performance …