Hershey, Pennsylvania
New York, New YorkBeijing, China
Exploration of Deep Learning and Transfer Learning Techniques in Bioinformatics

Exploration of Deep Learning and Transfer Learning Techniques in Bioinformatics

Sumit Bansal (Gurukula Kangri, Haridwar, India), Vandana Sindhi (Punjabi University, Patiala, India), and Bhim Sain Singla (Punjabi University, Patiala, India)
Copyright: © 2024 |Pages: 20
DOI: 10.4018/979-8-3693-1822-5.ch013
OnDemand:
(Individual Chapters)
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

The blend of profound learning and more learning techniques has brought about a worldview change in the creating subject of bioinformatics. The revolutionary environment that emerges when the complexity of biological data and artificial intelligence meet is the subject of this book chapter. The section explores profound learning models and moves learning closer, as well as the imaginative applications, hardships, and achievements that have developed at the crossing point of these two powerful fields. The section opens with a point-by-point assessment of profound learning standards and how they are applied to the unique difficulties of bioinformatics datasets. The section likewise digs into the idea of move learning—a strong worldview that utilizes information learned in one space to further develop execution in another. It has been shown that movement learning is powerful. The section likewise dives into the idea of move learning—a strong worldview that involves mastery in one region to further develop execution in another.
Chapter Preview
Top

2. Foundations Of Deep Learning In Bioinformatics

An extensive examination of deep learning techniques is covered in this section, along with an overview of CNN, RNN, LSTM, GAN, unsupervised learning, and the various uses of neural networks in bioinformatics. It also discusses the opportunities and difficulties specific to the deep learning discipline. The relationships between the fundamental components of deep learning in bioinformatics are shown in Figure 1.

2.1 Overview of Deep Learning Techniques

Deep learning is a type of machine learning that has transformed difficult data processing and interpretation. It is based on the structure and activities of the human brain and has emerged as a transformative force in a variety of industries. Deep learning algorithms have shown potential in bioinformatics for identifying significant patterns from huge biological datasets (Li et al., 2019). This section comprehensively introduces the core deep learning algorithms, as well as their structures, ideas, and bioinformatics applications.

2.2 Neural Networks: The Foundation of Deep Learning

Deep learning is based on a neural network, a computational model inspired by the neural architecture of the human brain. Neural networks handle information in a hierarchical manner by learning complex patterns and representations from input data via interconnected layers of nodes, or neurons (Thakur, 2021). Deep learning layers are the several levels that allow these networks to extract intricate connections and characteristics from input.

Figure 1.

Illustration depicting the interconnected foundations of deep learning in bioinformatics

979-8-3693-1822-5.ch013.f01

Complete Chapter List

Search this Book:
Reset