Latest Publications & Patents on Neural Networks

Neural Networks

Tip: further to this selection on Aeronautics, you can search and filter our:
    * free publications search tool * by author, topic, keywords, date or journal.
    * free patents search tool * for patents in English from the European Patent Office.

This is our latest selection of worldwide publications and patents in english on Neural Networks, between many scientific online journals, classified and focused on neural network, artificial neuron, epoch, neural architecture, machine learning, deep learning and support vector machine.

Patents: no recent patent on this particular topic. Please try the extensive manual search in the Patents Database linked just above.

Fast Prediction of Combustion Heat Release Rates for Dual-Fuel Engines Based on Neural Networks and Data Augmentation

Published on 2025-02-19 by Mingxin Wei, Xiuyun Shuai, Zexin Ma, Hongyu Liu, Qingxin Wang, Feiyang Zhao, Wenbin Yu @MDPI

Abstract: As emission regulations become increasingly stringent, diesel/natural gas dual-fuel engines are regarded as a promising solution and have attracted extensive research attention. However, their complex combustion processes pose significant challenges to traditional combustion modeling approaches. Data-driven modeling methods offer an effective way to capture the complexity of combustion processes, but their performance is critically constrained by the quantity and quality of the test data. To add[...]


Our summary: Fast prediction model based on neural networks and data augmentation for dual-fuel engines. Hybrid regression data augmentation architecture and Bayesian Neural Network for high-quality predictions. Adaptive weight allocation method for balanced accuracy distribution and enhanced generalization ability.

Neural Networks, Data Augmentation, Combustion Prediction, Dual-Fuel Engines

Publication

Automatic Configuration Search for Parameter-Efficient Fine-Tuning

Published on 2024-05-25 by Han Zhou, Xingchen Wan, Ivan Vuli?, Anna Korhonen @MIT

Abstract: Large pretrained language models are widely used in downstream NLP tasks via task-specific fine-tuning, but such procedures can be costly. Recently, Parameter-Efficient Fine-Tuning (PEFT) methods have achieved strong task performance while updating much fewer parameters than full model fine-tuning (FFT). However, it is non-trivial to make informed design choices on the PEFT configurations, such as their architecture, the number of tunable parameters, and even the layers in which the PEFT modules[...]


Our summary: Efficient fine-tuning method achieved with fewer parameters. AutoPEFT uses Bayesian optimization to discover optimal configurations. Outperforms existing methods on GLUE and SuperGLUE tasks. Pareto-optimal set balances performance and cost.

automatic configuration search, parameter-efficient fine-tuning, neural architecture search, pretrained language models, task-specific fine-tuning

Publication

Table of Contents
    Add a header to begin generating the table of contents

    AVAILABLE FOR NEW CHALLENGES
    Mechanical Engineer, Project, Process Engineering or R&D Manager
    Effective product development

    Available for a new challenge on short notice.
    Contact me on LinkedIn
    Plastic metal electronics integration, Design-to-cost, GMP, Ergonomics, Medium to high-volume devices & consumables, Lean Manufacturing, Regulated industries, CE & FDA, CAD, Solidworks, Lean Sigma Black Belt, medical ISO 13485

    We are looking for a new sponsor

     

    Your company or institution is into technique, science or research ?
    > send us a message <

    Topics covered: neural networks, artificial neuron, epoch, neural architecture, machine learning, deep learning, support vector machine, dynamic hand gesture recognition, benchmark datasets, pre-trained weights, training data, training dataset, design snapshots, Dendritic Neuron Model, synaptic plasticity, Reinforced Dynamic-grouping Differential Evolution, YOLOv8, and ByteTrack..

    Historical Context

    (if date is unknown or not relevant, e.g. "fluid mechanics", a rounded estimation of its notable emergence is provided)

    Scroll to Top

    You May Also Like