A hybrid neural architecture search for hyperspectral image classification
Frontiers in Physics, 2023 Convolution neural network (CNN)is widely used in hyperspectral image (HSI) classification. However, the network architecture of CNNs is usually designed manually, which requires careful fine-tuning.
Aili Wang +4 more
doaj +1 more source
Operation-level Progressive Differentiable Architecture Search
, 2021 Differentiable Neural Architecture Search (DARTS) is becoming more and more popular among Neural Architecture Search (NAS) methods because of its high search efficiency and low compute cost.
Jian Li +8 more
core +1 more source
Differentiable Neural Architecture Search for High-Dimensional Time Series Forecasting
IEEE Access, 2021 This study applies neural architecture search (NAS) techniques to the modeling of high-dimensional time series data such as multi-variate stock indices.
Renlong Jie, Junbin Gao
doaj +1 more source
Adaptive probabilistic load forecasting for individual buildings
iEnergy, 2022 Building-level load forecasting has become essential with the support of fine-grained data collected by widely deployed smart meters. It acts as a basis for arranging distributed energy resources, implementing demand response, etc. Compared to aggregated-
Chenxi Wang +5 more
doaj +1 more source
$\mu$DARTS: Model Uncertainty-Aware Differentiable Architecture Search [PDF]
, 2022 We present a Model Uncertainty-aware Differentiable ARchiTecture Search ($\mu$DARTS) that optimizes neural networks to simultaneously achieve high accuracy and low uncertainty.
Chakraborty, Biswadeep +1 more
core
Efficient Object Detection in SAR Images Based on Computation-Aware Neural Architecture Search
Applied Sciences, 2022 Remote sensing techniques are becoming more sophisticated as radar imaging techniques mature. Synthetic aperture radar (SAR) can now provide high-resolution images for day-and-night earth observation.
Chuanyou Li +6 more
doaj +1 more source
Improving Differentiable Architecture Search via Self-Distillation [PDF]
, 2023 Differentiable Architecture Search (DARTS) is a simple yet efficient Neural Architecture Search (NAS) method. During the search stage, DARTS trains a supernet by jointly optimizing architecture parameters and network parameters.
Wang, Weiping +3 more
core +1 more source
$β$-DARTS++: Bi-level Regularization for Proxy-robust Differentiable Architecture Search
CoRR, 2023 Neural Architecture Search has attracted increasing attention in recent years. Among them, differential NAS approaches such as DARTS, have gained popularity for the search efficiency. However, they still suffer from three main issues, that are, the weak stability due to the performance collapse, the poor generalization ability of the searched ...
Peng Ye 0006 +5 more
openaire +3 more sources
BaLeNAS:Differentiable Architecture Search via the Bayesian Learning Rule [PDF]
, 2022 Differentiable Architecture Search (DARTS) has received massive attention in recent years, mainly because it significantly reduces the computational cost through weight sharing and continuous relaxation.
Zhang, Miao +13 more
core +1 more source
Making Differentiable Architecture Search less local [PDF]
, 2021 Neural architecture search (NAS) is a recent methodology for automating the design of neural network architectures. Differentiable neural architecture search (DARTS) is a promising NAS approach that dramatically increases search efficiency.
Tomasi, Federico +2 more
core +2 more sources