Abstract
A single-layer neural network is the simplest type of neural networks laying the foundation for understanding other kinds of neural networks. There are no hidden layers in this network that only contains input and output layers. After the advent of the single-layer neural network, it took nearly 30 years for the multilayer neural perceptron (MLP) networks to emerge due to the lack of the right methods for reversing the calculated error to the hidden layers of MLPs. Unlike the single-layer neural networks, multilayer networks can be employed to learn nonlinear problems, as well as problems with multiple decisions. This chapter introduces the multilayer neural networks and how to perform the learning process with them. At the end of this chapter, the Keras library is utilized to gradually learn how to design a multilayer neural network for handwriting recognition.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
