☆ 4.7 Article

Variable three-term conjugate gradient method for training artificial neural networks

NEURAL NETWORKS (2023)

Related references

Note: Only part of the references are listed.

Article Computer Science, Artificial Intelligence

Deep neural network enabled corrective source term approach to hybrid analysis and modeling

Sindre Stenen Blakseth et al.

Summary: This paper introduces a novel approach to hybrid analysis and modeling called Corrective Source Term Approach (CoSTA). By using a deep neural network to generate a corrective source term, CoSTA outperforms other models in terms of predictive accuracy and generalization, while also providing a flexible yet solid theoretical foundation. The importance of CoSTA lies in its potential to allow data-driven techniques to enter high-stakes applications.

NEURAL NETWORKS (2022)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Efficient sampling-based inverse reliability analysis combining Monte Carlo simulation (MCS) and feedforward neural network (FNN)

Ungki Lee et al.

Summary: Inverse reliability analysis evaluates the percentile value of a performance function given a target reliability. This paper proposes an efficient and accurate sampling-based reliability analysis method using a feedforward neural network (FNN), without the need for a surrogate model. The method improves the accuracy of reliability analysis with the same number of samples or ensures the same accuracy with fewer samples. Comparative study shows that the proposed method is more accurate and computationally efficient than existing methods.

STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION (2022)

Add to Collection

Article Engineering, Mechanical

A health-adaptive time-scale representation (HTSR) embedded convolutional neural network for gearbox fault diagnostics

Yunhan Kim et al.

Summary: This research introduces a newly designed convolutional neural network (CNN) for gearbox fault diagnostics, which addresses the limitations of existing time-frequency analysis methods by proposing a health-adaptive time-scale representation (HTSR) embedded CNN. The HTSR approach includes multiscale convolutional filters and captures fault-related information through end-to-end learning.

MECHANICAL SYSTEMS AND SIGNAL PROCESSING (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Evolved explainable classifications for lymph node metastases

Iam Palatnik de Sousa et al.

Summary: This study presents a novel evolutionary approach for Explainable Artificial Intelligence, combining Local Interpretable Model Agnostic Explanations (LIME) with Multi-Objective Genetic Algorithms. The results show that this methodology can find high quality explanations and has the advantage of automated parameter fine tuning.

NEURAL NETWORKS (2022)

Add to Collection

Article Computer Science, Interdisciplinary Applications

A grasps-generation-and-selection convolutional neural network for a digital twin of intelligent robotic grasping

Weifei Hu et al.

Summary: This paper proposes a new grasps-generation-and-selection convolutional neural network (GGS-CNN) for robotic grasping. The GGS-CNN transforms RGB-D images into feature maps and evaluates the quality of selected grasps to generate grasp candidates. The proposed method achieves high success rates in grasping single objects and cluttered objects, and can obtain the best grasp in a short time.

ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING (2022)

Add to Collection

Article Engineering, Mechanical

Toward a Digital Twin: Time Series Prediction Based on a Hybrid Ensemble Empirical Mode Decomposition and BO-LSTM Neural Networks

Weifei Hu et al.

Summary: A hybrid time series prediction model based on EEMD-BO-LSTM neural networks is proposed, improving prediction accuracy by decomposing original time series into single-frequency signals and highly nonlinear, stochastic signals.

JOURNAL OF MECHANICAL DESIGN (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Bilateral attention decoder: A lightweight decoder for real-time semantic segmentation

Chengli Peng et al.

Summary: A lightweight bilateral attention decoder is proposed for real-time semantic segmentation in this paper, which improves spatial accuracy and efficiency through information refinement and fusion. The proposed method achieves better performance with higher inference speed compared to other state-of-the-art real-time and non-real-time semantic segmentation methods.

NEURAL NETWORKS (2021)

Add to Collection

Article Engineering, Mechanical

Multi-objective optimisation of hydro-pneumatic suspension with gas-oil emulsion for heavy-duty vehicles

Kihan Kwon et al.

VEHICLE SYSTEM DYNAMICS (2020)

Add to Collection

Article Robotics

Learning robust, real-time, reactive robotic grasping

Douglas Morrison et al.

INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH (2020)

Add to Collection

Article Engineering, Mechanical

Vehicle sideslip angle estimation using deep ensemble-based adaptive Kalman filter

Dongchan Kim et al.

MECHANICAL SYSTEMS AND SIGNAL PROCESSING (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

Hybrid multi-mode machine learning-based fault diagnosis strategies with application to aircraft gas turbine engines

Yanyan Shen et al.

NEURAL NETWORKS (2020)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Deep learning for determining a near-optimal topological design without any iteration

Yonggyun Yu et al.

STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION (2019)

Add to Collection

Article Robotics

On-Policy Dataset Synthesis for Learning Robot Grasping Policies Using Fully Convolutional Deep Networks

Vishal Satish et al.

IEEE ROBOTICS AND AUTOMATION LETTERS (2019)

Add to Collection

Article Robotics

Learning ambidextrous robot grasping policies

Jeffrey Mahler et al.

SCIENCE ROBOTICS (2019)

Add to Collection

Article Robotics

Deep learning for detecting robotic grasps

Ian Lenz et al.

INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH (2015)

Add to Collection

Article Computer Science, Software Engineering

Some descent three-term conjugate gradient methods and their global convergence

Li Zhang et al.

OPTIMIZATION METHODS & SOFTWARE (2007)

Add to Collection

Article Mathematics, Applied

A descent modified Polak-Ribiere-Polyak conjugate gradient method and its global convergence

Li Zhang et al.

IMA JOURNAL OF NUMERICAL ANALYSIS (2006)

Add to Collection

© Peeref 2019-2024. All rights reserved.