Opening book details…
Can I read Compositional Committees of Tiny Networks on EtoBox?
Compositional Committees of Tiny Networks by Goh Howe Seng; Tomas Maul; Manav Nitin Kapadnis is a book available to read on EtoBox.
What is Compositional Committees of Tiny Networks about?
Deep neural networks tend to be accurate but computationally expensive, whereas ensembles tend to be fast but do not capitalize on hierarchical representations. This paper proposes an approach that attempts to combine the advantages of both approaches. Hierarchical ensembles represent an effort in this direction, however they are not compositional in a representational sense, since they only combine classifier decisions and/or outputs. We propose to take this effort one step further in the form of compositional ensembles, which exploit the composition of the hidden representations of classifiers, here defined as tiny networks on account of being neural networks of significantly limited scale. As such, our particular instance of compositional ensembles is called Compositional Committee of Tiny Networks (CoCoTiNe). We experimented with different CoCoTiNe variants involving different types of composition, input usage, and ensemble decisions. The best variant demonstrated that CoCoTiNe is more accurate than standard hierarchical committees, and is relatable to the accuracy of vanilla Convolutional Neural Networks, whilst being 25.7 times faster in a standard CPU setup. In conclusion, t
- Author
- Goh Howe Seng; Tomas Maul; Manav Nitin Kapadnis
- Publisher
- Springer International Publishing : Imprint: Springer
- Published
- 2021
- Language
- EN
- ISBN
- 9783030922726
- Subjects
- Business, Computer Science, Engineering
More by Goh Howe Seng; Tomas Maul; Manav Nitin Kapadnis
Browse all works by Goh Howe Seng; Tomas Maul; Manav Nitin Kapadnis
Similar books
- Recurrent Neural Networks — Anthony L. Caterini, Dong Eui Chang, (2018)
- Cellular Neural Networks : Analysis, Design, and Optimization — Martin Hänggi; George S. Moschytz (2013)
- Bridging the Gap Between Reservoirs and Neural Networks — Masanori Hashimoto; Ángel López García-Arias; Jaehoon Yu (2023)
- Recognition of Handwritten Digits Using Neural Networks: A Review — Nayankumar Kadhre; Ketan Desale; Rohit More; Chaitanya Palghadmal (2022)
- Neural Networks Using C# Succinctly — James McCaffrey (2014)
- Networks — Patrick Jagoda (2017)