Results 21 to 30 of about 7,839,223 (287)
FP-NAS: Fast Probabilistic Neural Architecture Search [PDF]
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021 Differential Neural Architecture Search (NAS) requires all layer choices to be held in memory simultaneously; this limits the size of both search space and final architecture. In contrast, Probabilistic NAS, such as PARSEC, learns a distribution over high-performing architectures, and uses only as much memory as needed to train a single model ...
Zhicheng Yan 0001 +5 more
openaire +4 more sources
Differentiable neural architecture search in equivalent space with exploration enhancement [PDF]
, 2020 Recent works on One-Shot Neural Architecture Search (NAS) mostly adopt a bilevel optimization scheme to alternatively optimize the supernet weights and architecture parameters after relaxing the discrete search space into a differentiable space. However,
Chang, X +5 more
core +4 more sources
IMB-NAS: Neural Architecture Search for Imbalanced Datasets
CoRR, 2022 Class imbalance is a ubiquitous phenomenon occurring in real world data distributions. To overcome its detrimental effect on training accurate classifiers, existing work follows three major directions: class re-balancing, information transfer, and representation learning.
Rahul Duggal +3 more
openaire +2 more sources
Hierarchical quantum circuit representations for neural architecture search
npj Quantum Information, 2023 Quantum circuit algorithms often require architectural design choices analogous to those made in constructing neural and tensor networks. These tend to be hierarchical, modular and exhibit repeating patterns.
Matt Lourens +4 more
doaj +1 more source
FOX-NAS: Fast, On-device and Explainable Neural Architecture Search [PDF]
2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2021 Neural architecture search can discover neural networks with good performance, and One-Shot approaches are prevalent. One-Shot approaches typically require a supernet with weight sharing and predictors that predict the performance of architecture. However, the previous methods take much time to generate performance predictors thus are inefficient.
Chia-Hsiang Liu +5 more
openaire +4 more sources
Modified Neural Architecture Search (NAS) Using the Chromosome Non-Disjunction
Applied Sciences, 2021 This paper proposes a deep neural network structuring methodology through a genetic algorithm (GA) using chromosome non-disjunction. The proposed model includes methods for generating and tuning the neural network architecture without the aid of human ...
Kang-Moon Park +2 more
doaj +1 more source
NAS-Count: Counting-by-Density with Neural Architecture Search [PDF]
, 2020 Most of the recent advances in crowd counting have evolved from hand-designed density estimation networks, where multi-scale features are leveraged to address the scale variation problem, but at the expense of demanding design efforts. In this work, we automate the design of counting models with Neural Architecture Search (NAS) and introduce an end-to ...
Yutao Hu 0002 +6 more
openaire +4 more sources
NDARTS: A Differentiable Architecture Search Based on the Neumann Series
Algorithms, 2023 Neural architecture search (NAS) has shown great potential in discovering powerful and flexible network models, becoming an important branch of automatic machine learning (AutoML).
Xiaoyu Han +3 more
doaj +1 more source
Towards Leveraging Structure for Neural Predictor in NAS [PDF]
Computer and Knowledge Engineering, 2022 Neural Architecture Search (NAS), which automatically designs a neural architecture for a specific task, has attracted much attention in recent years. Properly defining the search space is a key step in the success of NAS approaches, which allows us to ...
Saeedeh Eslami +2 more
doaj +1 more source
NAS-NeRF: Generative Neural Architecture Search for Neural Radiance Fields
CoRR, 2023 Neural radiance fields (NeRFs) enable high-quality novel view synthesis, but their high computational complexity limits deployability. While existing neural-based solutions strive for efficiency, they use one-size-fits-all architectures regardless of scene complexity.
Saeejith Nair +3 more
openaire +2 more sources