Publication detail

FEECA: Design Space Exploration for Low-Latency and Energy-Efficient Capsule Network Accelerators

MARCHISIO, A. MRÁZEK, V. HANIF, M. SHAFIQUE, M.

Original Title

FEECA: Design Space Exploration for Low-Latency and Energy-Efficient Capsule Network Accelerators

Type

journal article in Web of Science

Language

English

Original Abstract

In the past few years, Capsule Networks (CapsNets) have taken the spotlight compared to traditional convolutional neural networks (CNNs) for image classification. Unlike CNNs, CapsNets have the ability to learn the spatial relationship between features of the images. However, their complexity grows because of their heterogeneous capsule structure and the dynamic routing, which is an iterative algorithm to dynamically learn the coupling coefficients of two consecutive capsule layers. This necessitates specialized hardware accelerators for CapsNets. Moreover, a high-performance and energy-efficient design of CapsNet accelerators requires exploration of different design decisions (such as the size and configuration of the processing array and the structure of the processing elements). Toward this, we make the following key contributions: 1) FEECA, a novel methodology to explore the design space of the (micro)architectural parameters of a CapsNet hardware accelerator and 2) CapsAcc, the first specialized RTL-level hardware architecture to perform CapsNets inference with high performance and high energy efficiency. Our CapsAcc achieves significant performance improvement, compared to an optimized GPU implementation, due to its efficient implementation of key activation functions, such as squash and softmax, and an efficient data reuse for the dynamic routing. The FEECA methodology employs the Non-dominated Sorting Genetic Algorithm (NSGA-II) to explore the Pareto-optimal points with respect to area, performance, and energy consumption. This requires analytical modeling of the number of clock cycles required to perform each operation of the CapsNet inference and the memory accesses to enable a fast yet accurate design space exploration. We synthesized the complete accelerator architecture in a 45-nm CMOS technology using Synopsys design tools and evaluated it for the MNIST benchmark (as done by the original CapsNet paper from Google Brain's team) and for a more complex data set, the German Traffic Sign Recognition Benchmark (GTSRB).

Keywords

capsule neural network, hardware accelerators, design space exploration

Authors

MARCHISIO, A.; MRÁZEK, V.; HANIF, M.; SHAFIQUE, M.

Released

1. 3. 2021

ISBN

1063-8210

Periodical

IEEE Trans. on VLSI Systems.

Year of study

29

Number

4

State

United States of America

Pages from

716

Pages to

729

Pages count

14

URL

BibTex

@article{BUT170049,
  author="MARCHISIO, A. and MRÁZEK, V. and HANIF, M. and SHAFIQUE, M.",
  title="FEECA: Design Space Exploration for Low-Latency and Energy-Efficient Capsule Network Accelerators",
  journal="IEEE Trans. on VLSI Systems.",
  year="2021",
  volume="29",
  number="4",
  pages="716--729",
  doi="10.1109/TVLSI.2021.3059518",
  issn="1063-8210",
  url="https://ieeexplore.ieee.org/document/9363276/"
}