Can I read Evolutionary Neural Architecture Search Supporting Approximate Multipliers on EtoBox?

Evolutionary Neural Architecture Search Supporting Approximate Multipliers by Michal Pinos; Vojtech Mrazek; Lukas Sekanina is a book available to read on EtoBox.

What is Evolutionary Neural Architecture Search Supporting Approximate Multipliers about?

There is a growing interest in automated neural architecture search (NAS) methods. They are employed to routinely deliver high-quality neural network architectures for various challenging data sets and reduce the designer's effort. The NAS methods utilizing multiobjective evolutionary algorithms are especially useful when the objective is not only to minimize the network error but also to minimize the number of parameters (weights) or power consumption of the inference phase. We propose a multi-objective NAS method based on Cartesian genetic programming for evolving convolutional neural networks (CNN). The method allows approximate operations to be used in CNNs to reduce power consumption of a target hardware implementation. During the NAS process, a suitable CNN architecture is evolved together with approximate multipliers to deliver the best trade-offs between the accuracy, network size and power consumption. The most suitable approximate multipliers are automatically selected from a library of approximate multipliers. Evolved CNNs are compared with common human-created CNNs of a similar complexity on the CIFAR-10 benchmark problem.

Author

Michal Pinos; Vojtech Mrazek; Lukas Sekanina

Publisher

Springer International Publishing : Imprint: Springer

Published

2021

Language

EN

ISBN

9783030728113

Subjects

Language Learning, Computer Science, Mathematics