Optimization Approaches in Meta-Learning Models

View Sample PDF

Author(s): Nidhi Arora (Lovely Professional University, India), Ashok Sharma (University of Jammu, India)and Dinesh Kumar (Maharaja Ranjit Singh Punjab Technical University, India)
Copyright: 2023
Pages: 11
Source title: Meta-Learning Frameworks for Imaging Applications
Source Author(s)/Editor(s): Ashok Sharma (University of Jammu, India), Sandeep Singh Sengar (Cardiff Metropolitan University, UK)and Parveen Singh (Cluster University, Jammu, India)
DOI: 10.4018/978-1-6684-7659-8.ch001

Keywords: Cognitive Informatics / Information Science Reference / Knowledge Management and Library Science / Machine Learning

Purchase

View Optimization Approaches in Meta-Learning Models on the publisher's website for pricing and purchasing information.

Abstract

This book chapter provides a comprehensive overview of optimization approaches in meta-learning, focusing on techniques and their applications. Meta-learning is a subfield of machine learning that emphasizes acquiring knowledge from previous tasks and applying the same to new tasks in order to develop the models with improved learning process. Optimization plays a crucial role in meta-learning models by enabling the effective acquisition and utilization of knowledge across tasks. This chapter provides an overview of various optimization approaches employed in meta-learning models which entail changing the model's input parameters or learning algorithms to facilitate effective learning across various tasks or domains. The methods tackle the problem of effective learning without compromising with accuracy and precision in performance focusing on the benefits of meta-learning frameworks in practical situations which may be considered as the real-world applications of these approaches.

The IRMA Community

Research IRM

Optimization Approaches in Meta-Learning Models

Purchase

Abstract

Related Content

IRMA Sponsors