TAS: Ternarized Neural Architecture Search for Resource-Constrained Edge Devices

Loni, Mohammad; Mousavi, Hamid; Riazati, Mohammad; Daneshtalab, Masoud; Sjödin, Mikael

doi:10.23919/date54114.2022.9774615

Cited by 9 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In DARTS, the type of each cell is either a normal cell for feature extraction or a reduction cell for both feature extraction and dimension reduction. After designing the optimal cell, we assemble the final network by stacking 18 normal cells with two reduction cells, where every six normal cells are followed by one reduction cell [37]. Last, the final architecture is re-trained from scratch to fine-tune the network parameters.…”

Section: Cnn Architecture Searchmentioning

confidence: 99%

Accurate Detection of Paroxysmal Atrial Fibrillation with Certified-GAN and Neural Architecture Search

Asadi

Poursalim

Loni

et al. 2023

Preprint

View full text Add to dashboard Cite

This paper presents a novel machine learning framework for detecting Paroxysmal Atrial Fib-rillation (PxAF), a pathological characteristic of Electrocardiogram (ECG) that can lead to fatalconditions such as heart attack. To enhance the learning process, the framework involves a Gen-erative Adversarial Network (GAN) along with a Neural Architecture Search (NAS) in the datapreparation and classifier optimization phases. The GAN is innovatively invoked to overcome theclass imbalance of the training data by producing the synthetic ECG for PxAF class in a certifiedmanner. The effect of the certified GAN is statistically validated. Instead of using a general-purposeclassifier, the NAS automatically designs a highly accurate convolutional neural network architecture customized for the PxAF classification task. Experimental results show that the accuracy of theproposed framework exhibits a high value of 99% which not only enhances state-of-the-art by up to5.1%, but also improves the classification performance of the two widely-accepted baseline methods,ResNet-18, and Auto-Sklearn, by 2.2% and 6.1%

show abstract

Section: Cnn Architecture Searchmentioning

confidence: 99%

Accurate Detection of Paroxysmal Atrial Fibrillation with Certified-GAN and Neural Architecture Search

Asadi

Poursalim

Loni

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…cell for feature extraction or a reduction cell for both feature extraction and dimension reduction. After designing the optimal cell, we assemble the final network by stacking 18 normal cells with two reduction cells, where every six normal cells are followed by one reduction cell [37]. Last, the final architecture is re-trained from scratch to fine-tune the network parameters.…”

Section: Cnn Architecture Searchmentioning

confidence: 99%

Accurate Detection of Paroxysmal Atrial Fibrillation with Certified-GAN and Neural Architecture Search

Asadi¹,

Poursalim²,

Loni³

et al. 2023

Preprint

View full text Add to dashboard Cite

This paper presents a novel machine learning framework for detecting Paroxysmal Atrial Fibrillation (PxAF), a pathological characteristic of Electrocardiogram (ECG) that can lead to fatal conditions such as heart attack. To enhance the learning process, the framework involves a Generative Adversarial Network (GAN) along with a Neural Architecture Search (NAS) in the data preparation and classifier optimization phases. The GAN is innovatively invoked to overcome the class imbalance of the training data by producing the synthetic ECG for PxAF class in a certified manner. The effect of the certified GAN is statistically validated. Instead of using a general-purpose classifier, the NAS automatically designs a highly accurate convolutional neural network architecture customized for the PxAF classification task. Experimental results show that the accuracy of the proposed framework exhibits a high value of 99% which not only enhances state-of-the-art by up to 5.1%, but also improves the classification performance of the two widely-accepted baseline methods, ResNet-18, and Auto-Sklearn, by 2.2% and 6.1%.

show abstract

“…In latency-sensitive systems, like autonomous driving and drone tracking, strict response time requirements must be satisfied. TAS [13] and DASS [14] have designed methods that combine quantization with NAS, and pruning with NAS, respectively. The goal of these methods is to reduce memory cost and speed up inference.…”

Section: Introductionmentioning

confidence: 99%

Latency-Constrained Neural Architecture Search Method for Efficient Model Deployment on RISC-V Devices

Xiang,

Ding,

Liu

et al. 2024

Electronics

View full text Add to dashboard Cite

The rapid development of the RISC-V instruction set architecture (ISA) has garnered significant attention in the realm of deep neural network applications. While hardware-aware neural architecture search (NAS) methods for ARM, X86, and GPUs have been extensively explored, research specifically targeting RISC-V remains limited. In light of this, we propose a latency-constrained NAS (LC-NAS) method specifically designed for RISC-V. This method enables efficient network searches without the requirement of network training. Concretely, in the training-free NAS framework, we introduce an RISC-V latency evaluation module that includes two implementations: a lookup table and a latency predictor based on a deep neural network. To obtain real latency data, we have designed a specialized data collection pipeline for RISC-V devices, which allows for precise end-to-end hardware latency measurements. We validate the effectiveness of our method in the NAS-Bench-201 search space. Experimental results demonstrate that our method can efficiently search for latency-constrained networks for RISC-V devices within seconds while maintaining high accuracy. Additionally, our method can easily integrate with existing training-free NAS approaches.

show abstract

TAS: Ternarized Neural Architecture Search for Resource-Constrained Edge Devices

Cited by 9 publications

References 10 publications

Accurate Detection of Paroxysmal Atrial Fibrillation with Certified-GAN and Neural Architecture Search

Accurate Detection of Paroxysmal Atrial Fibrillation with Certified-GAN and Neural Architecture Search

Accurate Detection of Paroxysmal Atrial Fibrillation with Certified-GAN and Neural Architecture Search

Latency-Constrained Neural Architecture Search Method for Efficient Model Deployment on RISC-V Devices

Contact Info

Product

Resources

About