NOTE: The following materials are presented for timely dissemination of academic and technical work. Copyright and all other rights therein are reserved by authors and/or other copyright holders. Persoanl use of the following materials is permitted and, however, people using the materials or information are expected to adhere to the terms and constraints invoked by the related copyright.

Deep and Modular Neural Netwoks


In this chapter, we focus on two important areas in neural computation, i.e., deep and modular neural networks, given the fact that both deep and modular neural networks have been among the most powerful machine learning and pattern recognition techniques for complex AI problem solving. We begin by providing a general overview of deep and modular neural networks to describe the general motivation behind such neural architectures and requirements for complex problem solving. Next, we describe background and motivation, methodologies, major building blocks, and the state-of-the-art hybrid learning strategy in context of deep neural architectures. Then, we describe background and motivation, taxonomy and learning algorithms pertaining to various yet typical modular neural network architectures. Furthermore, we also examine relevant issues and discuss open problems in deep and modular neural network areas.

Click Chapter 28 for full text.