• Home
  • Search
  • Auto-Adaptive Learning for Machine Perception of Native Accent Using Deep Learning
  • Cite Icon1
  • https://doi.org/10.1007/978-981-33-4389-4_58Copy DOI Icon

Auto-Adaptive Learning for Machine Perception of Native Accent Using Deep Learning

  • Jan 1, 2021
  • Mekala Srinivasa Rao +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

One of the solutions to artificial intelligence is machine learning. It enables us to create machines that can learn from experience rather than be programmed explicitly. Current formulations of machine learning are mostly designed with the help of data available for learning and performing specific tasks from neural networks. Deep learning is an effective machine learning approach that can solve multiple and specific tasks with mini mother change. Deep learning extends machine learning to multi-level distributed representations with the necessary mapping functions into a single composite function, and in particular neural networks. Along with their capability to learn dynamic hierarchical representations, the advent of deep learning and neural networks has opened up the way for continuous training. The main objective of this thesis is to research and establish a systematic approach to continuous learning that facilitates the success of profound education and neural networks.

Similar Papers
  • Book Chapter
  • Citations1

Deep Learning and Applications

  • Jan 01, 2017
  • Zhu Han +2
  • Research Article

Research progress in the application status and development trend of artificial intelligence in the diagnosis and treatment of spinal disease

  • Dec 16, 2019
  • Chinese Journal of Orthopaedics
  • Hanqiang Ouyang +4
  • Conference Article

Traffic Congestion Classification using Machine Learning

  • Dec 10, 2025
  • Maulik Mehrotra +2
  • Research Article
  • Citations6

Break through the limits of learning by machines

  • Sep 20, 2016
  • Chinese Science Bulletin
  • Zhongzhi Shi
  • Abstract
  • Citations24

Automated staging of knee osteoarthritis severity using deep neural networks

  • Apr 01, 2018
  • Osteoarthritis and Cartilage
  • S Suresha +4
  • Research Article
  • Citations33

Deep learning-a first meta-survey of selected reviews across scientific disciplines, their commonalities, challenges and research impact.

  • Nov 17, 2021
  • PeerJ Computer Science
  • Jan Egger +5
  • Dissertation
  • Citations5

Towards understanding the challenges faced by machine learning software developers and enabling automated solutions

  • Sep 04, 2020
  • Md Johirul Islam
  • Research Article

Towards Trustworthy Deep Learning

  • Mar 24, 2024
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Tsui-Wei (Lily) Weng
  • Research Article
  • Citations1

Advancements in Deep Learning for Autonomous Driving in Indian Road Conditions

  • Apr 15, 2024
  • Journal of Intelligent Data Analysis and Computational Statistics
  • Abdul Basith Maaz +4
  • PDF
  • Research Article
  • Citations2

Challenge of the performance management of trust control systems with deep learning

  • Mar 30, 2022
  • Advanced Engineering Research (Rostov-on-Don)
  • A A Zelensky +4
  • Book Chapter

TUTORIAL ON ARTIFICIAL NEURAL NETWORK

  • Dec 01, 2023
  • Loc Nguyen
  • Conference Article
  • Citations7

VAWS: Vulnerability Analysis of Neural Networks using Weight Sensitivity

  • Aug 01, 2019
  • Muluken Hailesellasie +3
  • Research Article
  • Citations111

A tutorial on deep learning-based data analytics in manufacturing through a welding case study

  • May 27, 2020
  • Journal of Manufacturing Processes
  • Qiyue Wang +3
  • PDF
  • Research Article
  • Citations42

Learning the Ising model with generative neural networks

  • Jun 02, 2020
  • Physical Review Research
  • Francesco D'Angelo +1
  • Book Chapter

Object Detection in Edge Environment: A Comparative Study of Algorithms and Use Cases

  • Jan 25, 2022
  • D Aishwarya +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.