Abstract
Artificial neural networks, conceptually and structurally inspired by neural systems, are of great interest along with deep learning, thanks to their great successes in various fields including medical imaging analysis. In this chapter, we describe the fundamental concepts and ideas of (deep) neural networks and explain algorithmic advances to learn network parameters efficiently by avoiding overfitting. Specifically, this chapter focuses on introducing (i) feed-forward neural networks, (ii) gradient descent-based parameter optimization algorithms, (iii) different types of deep models, (iv) technical tricks for fast and robust training of deep models, and (v) open source deep learning frameworks for quick practice.
| Original language | English |
|---|---|
| Title of host publication | Deep Learning for Medical Image Analysis |
| Publisher | Elsevier Inc. |
| Pages | 3-24 |
| Number of pages | 22 |
| ISBN (Electronic) | 9780128104095 |
| ISBN (Print) | 9780128104088 |
| DOIs | |
| Publication status | Published - 2017 Jan 30 |
Fingerprint
Keywords
- Convolutional neural network
- Deep belief network
- Deep Boltzmann machine
- Deep learning
- Neural networks
ASJC Scopus subject areas
- Engineering(all)
Cite this
An Introduction to Neural Networks and Deep Learning. / Suk, Heung-Il.
Deep Learning for Medical Image Analysis. Elsevier Inc., 2017. p. 3-24.Research output: Chapter in Book/Report/Conference proceeding › Chapter
}
TY - CHAP
T1 - An Introduction to Neural Networks and Deep Learning
AU - Suk, Heung-Il
PY - 2017/1/30
Y1 - 2017/1/30
N2 - Artificial neural networks, conceptually and structurally inspired by neural systems, are of great interest along with deep learning, thanks to their great successes in various fields including medical imaging analysis. In this chapter, we describe the fundamental concepts and ideas of (deep) neural networks and explain algorithmic advances to learn network parameters efficiently by avoiding overfitting. Specifically, this chapter focuses on introducing (i) feed-forward neural networks, (ii) gradient descent-based parameter optimization algorithms, (iii) different types of deep models, (iv) technical tricks for fast and robust training of deep models, and (v) open source deep learning frameworks for quick practice.
AB - Artificial neural networks, conceptually and structurally inspired by neural systems, are of great interest along with deep learning, thanks to their great successes in various fields including medical imaging analysis. In this chapter, we describe the fundamental concepts and ideas of (deep) neural networks and explain algorithmic advances to learn network parameters efficiently by avoiding overfitting. Specifically, this chapter focuses on introducing (i) feed-forward neural networks, (ii) gradient descent-based parameter optimization algorithms, (iii) different types of deep models, (iv) technical tricks for fast and robust training of deep models, and (v) open source deep learning frameworks for quick practice.
KW - Convolutional neural network
KW - Deep belief network
KW - Deep Boltzmann machine
KW - Deep learning
KW - Neural networks
UR - http://www.scopus.com/inward/record.url?scp=85027108481&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85027108481&partnerID=8YFLogxK
U2 - 10.1016/B978-0-12-810408-8.00002-X
DO - 10.1016/B978-0-12-810408-8.00002-X
M3 - Chapter
AN - SCOPUS:85027108481
SN - 9780128104088
SP - 3
EP - 24
BT - Deep Learning for Medical Image Analysis
PB - Elsevier Inc.
ER -