Abstract
Topology of a neural network refers to the way the neurons are connected, and it is an important factor in how the network functions and learns. A common topology in unsupervised learning is a direct map** of inputs to a collection of units that represents categories (e.g., self-organizing maps). A common topology in supervised learning is the fully connected, three-layer, feedforward network (see Backpropagation and Radial Basis Function Networks). In deep learning, however, many different topologies are used. Some models are dozens or even hundreds of layers deep (e.g., residual networks), others include complex recurrent structures (e.g., LSTM networks), and others include attentional structures (e.g., transformers). Much of the performance of the model depends on its topology, and neural architecture search, i.e., the process of determining the correct topology automatically using, for example, reinforcement learning or neuroevolution, has become a machine learning area of its own.
Similar content being viewed by others
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 Springer Science+Business Media, LLC, part of Springer Nature
About this entry
Cite this entry
Miikkulainen, R. (2023). Topology of a Neural Network. In: Phung, D., Webb, G.I., Sammut, C. (eds) Encyclopedia of Machine Learning and Data Science. Springer, New York, NY. https://doi.org/10.1007/978-1-4899-7502-7_843-2
Download citation
DOI: https://doi.org/10.1007/978-1-4899-7502-7_843-2
Published:
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4899-7502-7
Online ISBN: 978-1-4899-7502-7
eBook Packages: Springer Reference Computer SciencesReference Module Computer Science and Engineering
Publish with us
Chapter history
-
Latest
Topology of a Neural Network- Published:
- 07 December 2022
DOI: https://doi.org/10.1007/978-1-4899-7502-7_843-2
-
Original
Topology of a Neural Network- Published:
- 29 April 2015
DOI: https://doi.org/10.1007/978-1-4899-7502-7_843-1