Neural Architecture Search for Energy Efficient Always-on Audio Models
- URL: http://arxiv.org/abs/2202.05397v2
- Date: Thu, 1 Jun 2023 12:05:05 GMT
- Title: Neural Architecture Search for Energy Efficient Always-on Audio Models
- Authors: Daniel T. Speckhard, Karolis Misiunas, Sagi Perel, Tenghui Zhu, Simon
Carlile, Malcolm Slaney
- Abstract summary: We present several changes to neural architecture searches (NAS) that improve the chance of success in practical situations.
We benchmark the performance of our search on real hardware, but since running thousands of tests with real hardware is difficult we use a random forest model to roughly predict the energy usage of a candidate network.
Our search, evaluated on a sound-event classification dataset based upon AudioSet, results in an order of magnitude less energy per inference and a much smaller memory footprint.
- Score: 1.3846912186423144
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Mobile and edge computing devices for always-on classification tasks require
energy-efficient neural network architectures. In this paper we present several
changes to neural architecture searches (NAS) that improve the chance of
success in practical situations. Our search simultaneously optimizes for
network accuracy, energy efficiency and memory usage. We benchmark the
performance of our search on real hardware, but since running thousands of
tests with real hardware is difficult we use a random forest model to roughly
predict the energy usage of a candidate network. 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. Our
search, evaluated on a sound-event classification dataset based upon AudioSet,
results in an order of magnitude less energy per inference and a much smaller
memory footprint than our baseline MobileNetV1/V2 implementations while
slightly improving task accuracy. We also demonstrate how combining a 2D
spectrogram with a convolution with many filters causes a computational
bottleneck for audio classification and that alternative approaches reduce the
computational burden but sacrifice task accuracy.
Related papers
- Task-Oriented Real-time Visual Inference for IoVT Systems: A Co-design Framework of Neural Networks and Edge Deployment [61.20689382879937]
Task-oriented edge computing addresses this by shifting data analysis to the edge.
Existing methods struggle to balance high model performance with low resource consumption.
We propose a novel co-design framework to optimize neural network architecture.
arXiv Detail & Related papers (2024-10-29T19:02:54Z) - Neural network scoring for efficient computing [0.9124662097191377]
We introduce a composite score that aims to characterize the trade-off between accuracy and power consumption measured during the inference of neural networks.
To our best knowledge, it is the first fit test for neural architectures on hardware architectures.
arXiv Detail & Related papers (2023-10-14T10:29:52Z) - Simple Pooling Front-ends For Efficient Audio Classification [56.59107110017436]
We show that eliminating the temporal redundancy in the input audio features could be an effective approach for efficient audio classification.
We propose a family of simple pooling front-ends (SimPFs) which use simple non-parametric pooling operations to reduce the redundant information.
SimPFs can achieve a reduction in more than half of the number of floating point operations for off-the-shelf audio neural networks.
arXiv Detail & Related papers (2022-10-03T14:00:41Z) - NAS-FCOS: Efficient Search for Object Detection Architectures [113.47766862146389]
We propose an efficient method to obtain better object detectors by searching for the feature pyramid network (FPN) and the prediction head of a simple anchor-free object detector.
With carefully designed search space, search algorithms, and strategies for evaluating network quality, we are able to find top-performing detection architectures within 4 days using 8 V100 GPUs.
arXiv Detail & Related papers (2021-10-24T12:20:04Z) - Broadcasted Residual Learning for Efficient Keyword Spotting [7.335747584353902]
We present a broadcasted residual learning method to achieve high accuracy with small model size and computational load.
We also propose a novel network architecture, Broadcasting-residual network (BC-ResNet), based on broadcasted residual learning.
BC-ResNets achieve state-of-the-art 98.0% and 98.7% top-1 accuracy on Google speech command datasets v1 and v2, respectively.
arXiv Detail & Related papers (2021-06-08T06:55:39Z) - Ps and Qs: Quantization-aware pruning for efficient low latency neural
network inference [56.24109486973292]
We study the interplay between pruning and quantization during the training of neural networks for ultra low latency applications.
We find that quantization-aware pruning yields more computationally efficient models than either pruning or quantization alone for our task.
arXiv Detail & Related papers (2021-02-22T19:00:05Z) - MS-RANAS: Multi-Scale Resource-Aware Neural Architecture Search [94.80212602202518]
We propose Multi-Scale Resource-Aware Neural Architecture Search (MS-RANAS)
We employ a one-shot architecture search approach in order to obtain a reduced search cost.
We achieve state-of-the-art results in terms of accuracy-speed trade-off.
arXiv Detail & Related papers (2020-09-29T11:56:01Z) - EagerNet: Early Predictions of Neural Networks for Computationally
Efficient Intrusion Detection [2.223733768286313]
We propose a new architecture to detect network attacks with minimal resources.
The architecture is able to deal with either binary or multiclass classification problems and trades prediction speed for the accuracy of the network.
arXiv Detail & Related papers (2020-07-27T11:31:37Z) - Latency-Aware Differentiable Neural Architecture Search [113.35689580508343]
Differentiable neural architecture search methods became popular in recent years, mainly due to their low search costs and flexibility in designing the search space.
However, these methods suffer the difficulty in optimizing network, so that the searched network is often unfriendly to hardware.
This paper deals with this problem by adding a differentiable latency loss term into optimization, so that the search process can tradeoff between accuracy and latency with a balancing coefficient.
arXiv Detail & Related papers (2020-01-17T15:55:21Z) - Neural Architecture Search on Acoustic Scene Classification [13.529070650030313]
We propose a lightweight yet high-performing baseline network inspired by MobileNetV2.
We explore a dynamic architecture space built on the basis of the proposed baseline.
Experimental results demonstrate that our searched network is competent in ASC tasks.
arXiv Detail & Related papers (2019-12-30T06:35:12Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.