Results 91 to 100 of about 7,839,223 (287)

Overview of Differentiable Neural Network Architecture Search

Zhengzhou Daxue xuebao. Gongxue ban
Neural Architecture Search (NAS) was an interdisciplinary study in the field of deep learning, which aimed to automate the design of neural network structures. NAS required repeated training and evaluation of a large number of candidate networks, which
LU Peng, LI Keyan, ZHANG Hongpo, CHEN Liwei, WU Jiahui, LIU Shuaibing   +5 more
doaj   +1 more source

Neural Architecture Search (NAS)

Neural Architecture Search ...
Ioannis Kourouklides
core   +1 more source

Neural architecture search

, 2022
Neural Architecture Search is a technique for designing neural network architectures with minimal human intervention by allowing an algorithm to search through an architecture space to find an optimal architecture design.
Chang, Chuan Hong
core  

Observer‐Based Adaptive Event‐Triggered Tracking Control for Fuzzy TS Systems With Premise Mismatch

International Journal of Adaptive Control and Signal Processing, EarlyView.
This paper presents an adaptive logistic event‐triggered observer‐based tracking controller for Takagi‐Sugeno fuzzy systems under constrained inputs and network delays. Leveraging a hybrid LMI and Secretary Bird Optimization approach, this strategy significantly minimizes communication overhead and computational burden while ensuring optimal reference ...
Oussama Djadane, Salama Makni, Mourad Kchaou, Ahmed El Hajjaji   +3 more
wiley   +1 more source

dynoGP: Deep Gaussian Processes for Dynamic System Identification

International Journal of Adaptive Control and Signal Processing, EarlyView.
This work introduces a novel class of deep models for system identification, dynamical deep Gaussian processes, which combine the strengths of data‐driven methods, such as those based on neural network architectures, with the ability to output a probability distribution for uncertainty representation.
Alessio Benavoli, Marco Forgione, Dario Piga, Marco Zaffalon   +3 more
wiley   +1 more source

CP-NAS: Child-Parent Neural Architecture Search for Binary Neural Networks

CoRR, 2020
Neural architecture search (NAS) proves to be among the best approaches for many tasks by generating an application-adaptive neural architecture, which is still challenged by high computational cost and memory consumption. At the same time, 1-bit convolutional neural networks (CNNs) with binarized weights and activations show their potential for ...
Li'an Zhuo, Baochang Zhang 0001, Hanlin Chen, Linlin Yang, Chen Chen 0001, Yanjun Zhu, David S. Doermann   +6 more
openaire   +2 more sources

Neural Architecture Search for Convolutional and Transformer Deep Neural Networks [PDF]

, 2023
Deep Neural Networks (DNN) have dominated computer vision tasks during the last decade. However, in recent years, the demand for highly customized deep neural networks has increased significantly, which has made manual design of architectures a tedious
Chen, Boyu
core  

A Numerical–Experimental Approach for Multi‐Matrix Fiber‐Reinforced Plastics Characterization Using Finite Element Model Updating

Advanced Engineering Materials, EarlyView.
A numerical–experimental framework is developed for characterizing multi‐matrix fiber‐reinforced polymers (MM‐FRPs) combining epoxy and polyurethane matrices. Harmonic bending tests are integrated with finite element model updating (FEMU) to simultaneously identify elastic and viscoelastic material parameters.
Rodrigo M. Dartora, Tales V. Lisbôa, Axel Spickenheuer, Rogério J. Marczak, Jakson M. Vassoler   +4 more
wiley   +1 more source

Architecture-aware minimization (A2M): how to find flat minima in neural architecture search

Machine Learning: Science and Technology
Neural architecture search (NAS) has become an essential tool for designing effective and efficient neural networks. In this paper, we investigate the geometric properties of neural architecture spaces commonly used in differentiable NAS methods ...
Matteo Gambella, Fabrizio Pittorino, Manuel Roveri   +2 more
doaj   +1 more source

NAS-Bench-101: Towards Reproducible Neural Architecture Search

CoRR, 2019
Recent advances in neural architecture search (NAS) demand tremendous computational resources, which makes it difficult to reproduce experiments and imposes a barrier-to-entry to researchers without access to large-scale computation. We aim to ameliorate these problems by introducing NAS-Bench-101, the first public architecture dataset for NAS research.
Chris Ying, Aaron Klein, Eric Christiansen, Esteban Real, Kevin Murphy 0002, Frank Hutter   +5 more
openaire   +3 more sources