University of Sussex
Browse

Fast deep neural architecture search for wearable activity recognition by early prediction of converged performance

Download (647.82 kB)
conference contribution
posted on 2023-06-10, 00:52 authored by Lloyd Pellatt, Daniel RoggenDaniel Roggen
Neural Architecture Search (NAS) has the potential to uncover more performant networks for wearable activity recognition, but a naive evaluation of the search space is computationally expensive. We introduce neural regression methods for predicting the converged performance of a Deep Neural Network (DNN) using validation performance in early epochs and topological and computational statistics. Our approach shows a significant improvement in predicting converged testing performance. We apply this to the optimisation of the convolutional feature extractor of an LSTM recurrent network using NAS with deep Q-learning, optimising the kernel size, number of kernels, number of layers and the connections between layers, allowing for arbitrary skip connections and dimensionality reduction with pooling layers. We find architectures which achieve up to 4% better F1 score on the recognition of gestures in the Opportunity dataset than our implementation of the state of the art model DeepConvLSTM, while reducing the search time by >90% over a random search. This opens the way to rapidly search for well performing dataset-specific architectures.

History

Publication status

  • Published

File Version

  • Accepted version

Journal

Proceedings of the International Symposium on Wearable Computing 2021

Publisher

ACM

Page range

1-6

Event name

The International Symposium on Wearable Computing 2021

Event location

Virtual

Event type

conference

Event date

21–26th September 2021

ISBN

9781450384629

Department affiliated with

  • Engineering and Design Publications

Full text available

  • Yes

Peer reviewed?

  • Yes

Legacy Posted Date

2021-09-07

First Open Access (FOA) Date

2021-09-07

First Compliant Deposit (FCD) Date

2021-09-07

Usage metrics

    University of Sussex (Publications)

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC