NASCaps: A Framework for Neural Architecture Search to Optimize the Accuracy and Hardware Efficiency of Convolutional Capsule Networks

Alberto Marchisio, Andrea Massa, Vojtech Mrazek, Beatrice Bussolino, Maurizio Martina, Muhammad Shafique

Research output: Contribution to journalConference articlepeer-review

Abstract

Deep Neural Networks (DNNs) have made significant improvements to reach the desired accuracy to be employed in a wide variety of Machine Learning (ML) applications. Recently the Google Brain's team demonstrated the ability of Capsule Networks (CapsNets) to encode and learn spatial correlations between different input features, thereby obtaining superior learning capabilities compared to traditional (i.e., non-capsule based) DNNs. However, designing CapsNets using conventional methods is a tedious job and incurs significant training effort. Recent studies have shown that powerful methods to automatically select the best/optimal DNN model configuration for a given set of applications and a training dataset are based on the Neural Architecture Search (NAS) algorithms. Moreover, due to their extreme computational and memory requirements, DNNs are employed using the specialized hardware accelerators in IoT-Edge/CPS devices. In this paper, we propose NASCaps, an automated framework for the hardware-aware NAS of different types of DNNs, covering both traditional convolutional DNNs and CapsNets. We study the efficacy of deploying a multi-objective Genetic Algorithm (e.g., based on the NSGA-II algorithm). The proposed framework can jointly optimize the network accuracy and the corresponding hardware efficiency, expressed in terms of energy, memory, and latency of a given hardware accelerator executing the DNN inference. Besides supporting the traditional DNN layers (such as, convolutional and fully-connected), our framework is the first to model and supports the specialized capsule layers and dynamic routing in the NAS-flow. We evaluate our framework on different datasets, generating different network configurations, and demonstrate the tradeoffs between the different output metrics. We will open-source the complete framework and configurations of the Pareto-optimal architectures at https://github.com/ehw-fit/nascaps.

Original languageEnglish (US)
Article number9256635
JournalIEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD
Volume2020-November
DOIs
StatePublished - Nov 2 2020
Event39th IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2020 - Virtual, San Diego, United States
Duration: Nov 2 2020Nov 5 2020

Keywords

  • Accuracy
  • Capsule Networks
  • Deep Neural Networks
  • Design Space
  • DNNs
  • Energy Efficiency
  • Evolutionary Algorithms
  • Genetic Algorithms
  • Hardware Accelerators
  • Latency
  • Memory
  • Multi-Objective
  • Neural Architecture Search
  • Optimization

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Computer Graphics and Computer-Aided Design

Fingerprint Dive into the research topics of 'NASCaps: A Framework for Neural Architecture Search to Optimize the Accuracy and Hardware Efficiency of Convolutional Capsule Networks'. Together they form a unique fingerprint.

Cite this