Deep Learning and Biomedical Engineering

Deep Learning and Biomedical Engineering

Suraj Sawant (College of Engineering Pune, India)
DOI: 10.4018/978-1-5225-4769-3.ch014
OnDemand PDF Download:
No Current Special Offers


Deep learning (DL) is a method of machine learning, as running over artificial neural networks, which has a structure above the standards to deal with large amounts of data. That is generally because of the increasing amount of data, input data sizes, and of course, greater complexity of objective real-world problems. Performed research studies in the associated literature show that the DL currently has a good performance among considered problems and it seems to be a strong solution for more advanced problems of the future. In this context, this chapter aims to provide some essential information about DL and its applications within the field of biomedical engineering. The chapter is organized as a reference source for enabling readers to have an idea about the relation between DL and biomedical engineering.
Chapter Preview

Deep Learning

Before discussing about Deep Learning and Biomedical Engineering, it is a good idea to briefly introduce the concept of Deep Learning and take a look at to its application ways.

The Concept of Deep Learning

In the past few years, Deep Learning (DL) has rapidly evolved into the de-facto approach, showing tremendous improvement in accuracy, robustness, and cross-language generalizability over conventional approaches (Deng & Yu, 2014). DL also termed as Hierarchical Learning or Deep Structured Learning in some of the literature work is a technique of Information Processing. It is a sub-set of machine learning methods. It is the process of training and learning from Artificial Neural Networks (ANNs) containing more than one hidden layer. DL allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in drug discovery and genomics. DL discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional networks have brought about breakthroughs in processing bio medical images, video, speech and audio, whereas recurrent networks have shone light on sequential data such as text and speech (LeCun et al., 2015). To date, DL has emerged as the leading machine-learning tool in the general imaging and computer vision domains. DL is a growing trend in general data analysis and was termed as one of the 10 breakthrough technologies of 2013 (MIT Tech. Review, 2013). DL has improved day by time till nowadays as an important approach for the future of intelligent systems.

Complete Chapter List

Search this Book: