Understanding Convolutional Neural Network With TensorFlow: CNN

View Sample PDF

Author(s): Aswathy Ravikumar (Vellore Institute of Technology, Chennai, India)and Harini Sriraman (Vellore Institute of Technology, Chennai, India)
Copyright: 2024
Pages: 24
Source title: Machine Learning Algorithms Using Scikit and TensorFlow Environments
Source Author(s)/Editor(s): Puvvadi Baby Maruthi (Dayananda Sagar University, India), Smrity Prasad (Dayananda Sagar University, India)and Amit Kumar Tyagi ( National Institute of Fashion Technology, New Delhi, India)
DOI: 10.4018/978-1-6684-8531-6.ch003

Keywords: Engineering Science Reference / Knowledge Management and Library Science / Machine Learning / Systems and Software Engineering

Purchase

View Understanding Convolutional Neural Network With TensorFlow: CNN on the publisher's website for pricing and purchasing information.

Abstract

In academia and business, deep-learning-based models have exhibited extraordinary performance over the last decade. The learning potential of Convolutional Neural Networks (CNNs) derives from a combination of several feature extraction levels that completely use a vast quantity of input. CNN is an important technique for tackling computer vision issues, although the theories behind its processing efficacy are not yet completely understood. CNN has achieved cutting-edge performance on a variety of datasets in computer vision applications like remote sensing, medical image categorization, facial detection, and object identification. This is due to the efficiency with which they process visual features. This chapter presents the most significant advancements in CNN for efficient processing in computer vision, including convolutional layer configurations, pooling layer approaches, network activation functions, loss functions, normalization approaches, and CNN optimization techniques.

The IRMA Community

Research IRM

Understanding Convolutional Neural Network With TensorFlow: CNN

Purchase

Abstract

Related Content

IRMA Sponsors