Neural Architecture Search for Energy Efficient Always-on Audio Models

02/09/2022
by   Daniel T. Speckhard, et al.
12

Mobile and edge computing devices for always-on audio classification require energy-efficient neural network architectures. We present a neural architecture search (NAS) that optimizes accuracy, energy efficiency and memory usage. The search is run on Vizier, a black-box optimization service. We present a search strategy that uses both Bayesian and regularized evolutionary search with particle swarms, and employs early-stopping to reduce the computational burden. The search returns architectures for a sound-event classification dataset based upon AudioSet with similar accuracy to MobileNetV1/V2 implementations but with an order of magnitude less energy per inference and a much smaller memory footprint.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/09/2023

Carbon-Efficient Neural Architecture Search

This work presents a novel approach to neural architecture search (NAS) ...
research
02/13/2019

Probabilistic Neural Architecture Search

In neural architecture search (NAS), the space of neural network archite...
research
03/19/2023

ERSAM: Neural Architecture Search For Energy-Efficient and Real-Time Social Ambiance Measurement

Social ambiance describes the context in which social interactions happe...
research
07/22/2019

MemNet: Memory-Efficiency Guided Neural Architecture Search with Augment-Trim learning

Recent studies on automatic neural architectures search have demonstrate...
research
10/07/2019

Energy-Aware Neural Architecture Optimization with Fast Splitting Steepest Descent

Designing energy-efficient networks is of critical importance for enabli...
research
04/21/2021

Carbon Emissions and Large Neural Network Training

The computation demand for machine learning (ML) has grown rapidly recen...
research
03/28/2022

Robust and Energy-efficient PPG-based Heart-Rate Monitoring

A wrist-worn PPG sensor coupled with a lightweight algorithm can run on ...

Please sign up or login with your details

Forgot password? Click here to reset