Neural Architecture Search Benchmarks: Insights and Survey

Chitty-Venkata, Krishna Teja; Emani, Murali; Vishwanath, Venkatram; Somani, Arun K.

doi:10.1109/access.2023.3253818

Cited by 20 publications

(11 citation statements)

References 82 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While CNNs are widely known for their success in image processing [19], they have also shown promising results in speech-related applications, such as speech recognition, speaker identification, and emotion recognition [21]. While significant progress has been made in developing automated neural architecture search in recent years [22], identifying the optimal architecture remains a challenging task that continues to rely on specific case studies and expert knowledge. In this work, the proposed AE model has been designed through an iterative trial-and-error process, involving adjustments to the number of layers, the number of neurons per layer, and the hyperparameter values.…”

Section: A Neural Network Architecturementioning

confidence: 99%

Automatic Audio Feature Extraction for Keyword Spotting

Vitolo,

Liguori,

Benedetto

et al. 2024

IEEE Signal Process. Lett.

View full text Add to dashboard Cite

The accuracy and computational complexity of keyword spotting (KWS) systems are heavily influenced by the choice of audio features in speech signals. This paper introduces a novel approach for audio feature extraction in KWS by leveraging a convolutional autoencoder, which has not been explored in the existing literature. Strengths of the proposed approach are in the ability to automate the extraction of the audio features, keep its computational complexity low, and allow accuracy values of the overall KWS systems comparable with the state of the art. To evaluate the effectiveness of our proposal, we compared it with the widely-used Mel Frequency Cepstrum (MFC) method in terms of classification metrics in noisy conditions and the number of required operators, using the public Google speech command dataset. Results demonstrate that the proposed audio feature extractor achieves an average classification accuracy on 12 classes ranging from 81.84% to 90.36% when the signal-tonoise ratio spans from 0 to 40 dB, outperforming the MFC up to 5.2%. Furthermore, the required number of operations is one order of magnitude lower than that of the MFC, resulting in a reduction in computational complexity and processing time, which makes it well-suited for integration with KWS systems in resource-constrained edge devices.

show abstract

Section: A Neural Network Architecturementioning

confidence: 99%

Automatic Audio Feature Extraction for Keyword Spotting

Vitolo,

Liguori,

Benedetto

et al. 2024

IEEE Signal Process. Lett.

View full text Add to dashboard Cite

show abstract

“…2) Neural Architecture Search for Convolutions: Neural Architecture Search (NAS) is an automated approach to designing CNN architectures [76] [81]. Instead of relying on humandesigned architectures, NAS employs search algorithms and neural networks to discover architectures that perform well on specific applications [76]. This technique has led to the development of state-of-the-art CNNs that outperform handcrafted models [299]- [309].…”

Section: F Recent Advancements and Innovationsmentioning

confidence: 99%

A Novel Levy Walk-Based Framework for Scheduling Power-Intensive Mobile Edge Computing Tasks

Younesi,

Fazli,

Ejlali

2023

Preprint

View full text Add to dashboard Cite

“…Utilizing this self-built prototype system, we successfully obtained hyperspectral images of four distinct bacterial pathogens and analyzed their spectral differences. Additionally, inspired by the great achievements of the Transformer network in the field of natural language processing (NLP) and image processing, such as ChatGPT, ViT, and so on [23]. This article is dedicated to extending the network architecture to identify hyperspectral images of infectious pathogens.…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral upgrade solution for biomicroscope combined withTransformernetwork to classify infectious bacteria

Lu,

Zhang,

Wang

et al. 2024

Journal of Biophotonics

View full text Add to dashboard Cite

Infectious diseases caused by bacterial pathogens pose a significant public health threat, emphasizing the need for swift and accurate bacterial species detection methods. Hyperspectral microscopic imaging (HMI) offers nondestructive, rapid, and data‐rich advantages, making it a promising tool for microbial detection. In this research, we present a highly compatible and cost‐effective approach to extend a standard biomicroscope system into a hyperspectral biomicroscope using a prism‐grating‐prism configuration. Using this prototype, we generate 600 hyperspectral data cubes for Listeria, Bacillus typhi, Bacillus pestis, and Bacillus anthracis. Additionally, we propose a Transformer‐based classification network that achieves a 99.44% accuracy in classifying these infectious pathogens, outperforming traditional methods. Our results suggest that the successful combination of HMI and the optimized Transformer‐based classification network highlights the potential for rapid and precise detection of infectious disease pathogens .

show abstract

Neural Architecture Search Benchmarks: Insights and Survey

Cited by 20 publications

References 82 publications

Automatic Audio Feature Extraction for Keyword Spotting

Automatic Audio Feature Extraction for Keyword Spotting

A Novel Levy Walk-Based Framework for Scheduling Power-Intensive Mobile Edge Computing Tasks

Hyperspectral upgrade solution for biomicroscope combined withTransformernetwork to classify infectious bacteria

Contact Info

Product

Resources

About