Results 11 to 20 of about 6,207,310 (278)
DDNAS: Discretized Differentiable Neural Architecture Search for Text Classification
ACM Transactions on Intelligent Systems and Technology, 2023 Neural Architecture Search (NAS) has shown promising capability in learning text representation. However, existing text-based NAS neither performs a learnable fusion of neural operations to optimize the architecture nor encodes the latent hierarchical categorization behind text input. This article presents a novel NAS method, Discretized Differentiable
Kuan-Chun Chen +2 more
openaire +4 more sources
MDARTS: Multi-objective Differentiable Neural Architecture Search
2021 Design, Automation & Test in Europe Conference & Exhibition (DATE), 2021 In this work, we present a differentiable neural architecture search (NAS) method that takes into account two competing objectives, quality of result (QoR) and quality of service (QoS) with hardware design constraints. NAS research has recently received a lot of attention due to its ability to automatically find architecture candidates that can ...
Sunghoon Kim +5 more
openaire +3 more sources
Search Space Adaptation for Differentiable Neural Architecture Search in Image Classification
2022 Thirteenth International Conference on Ubiquitous and Future Networks (ICUFN), 2022 As deep neural networks achieve unprecedented performance in various tasks, neural architecture search (NAS), a research field for designing neural network architectures with automated processes, is actively underway. More recently, differentiable NAS has a great impact by reducing the search cost to the level of training a single network. Besides, the
Youngkee Kim +3 more
openaire +5 more sources
Neural Architecture Search via Differentiable Proxies in AUTOML
Eduschool International Journal of Data Science and Machine learning (EIJDSML)Neural Architecture Search (NAS) automates the design of deep neural network architectures, potentially surpassing human-crafted designs across diverse tasks. However, the computational cost of evaluating candidate architectures has historically limited NAS scalability, with early methods requiring thousands of GPU-hours per search.
Rejina P V
openaire +3 more sources
DSRNA: Differentiable Search of Robust Neural Architectures [PDF]
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021 10 ...
Ramtin Hosseini +2 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
Symbolic Neural Architecture Search for Differential Equations
IEEE Access, 2023 In this paper, we introduce the first use of symbolic integration that leverages the machine learning infrastructure, such as automatic differentiation, to find analytical approximations of ordinary and partial differential equations. Analytical solutions to differential equations are at the core of fundamental mathematical models, which often cannot ...
Paulius Sasnauskas, Linas Petkevicius
openaire +3 more sources
E-DNAS: Differentiable Neural Architecture Search for Embedded Systems [PDF]
2020 25th International Conference on Pattern Recognition (ICPR), 2021 Trabajo presentado en el 25th International Conference on Pattern Recognition (ICPR), celebrado en Milán (Italia), del 10 al 15 de enero de ...
García López, Javier +2 more
openaire +3 more sources
Differential Evolution for Neural Architecture Search
CoRR, 2020 Neural architecture search (NAS) methods rely on a search strategy for deciding which architectures to evaluate next and a performance estimation strategy for assessing their performance (e.g., using full evaluations, multi-fidelity evaluations, or the one-shot model). In this paper, we focus on the search strategy. We introduce the simple yet powerful
Noor H. Awad +2 more
openaire +2 more sources
DASS: Differentiable Architecture Search for Sparse Neural Networks
ACM Transactions on Embedded Computing Systems, 2023 The deployment of Deep Neural Networks (DNNs) on edge devices is hindered by the substantial gap between performance requirements and available computational power. While recent research has made significant strides in developing pruning methods to build a sparse network for reducing the computing overhead of DNNs, there remains considerable accuracy ...
Hamid Mousavi +3 more
openaire +3 more sources