Umeå universitets logga

umu.sePublikationer
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Towards safe and efficient application of deep neural networks in resource-constrained real-time embedded systems
Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för tillämpad fysik och elektronik.
2023 (Engelska)Doktorsavhandling, sammanläggning (Övrigt vetenskapligt)
Abstract [en]

We consider real-time safety-critical systems that feature closed-loop interactions between the embedded computing system and the physical environment with a sense-compute-actuate feedback loop. Deep Learning (DL) with Deep Neural Networks (DNNs) has achieved success in many application domains, but there are still significant challenges in its application in real-time safety-critical systems that require high levels of safety certification under significant hardware resource constraints. This thesis considers the following overarching research goal: How to achieve safe and efficient application of DNNs in resource-constrained Real-Time Embedded (RTE) systems in the context of safety-critical application domains such as Autonomous Driving? Towards reaching that goal, this thesis presents a set of algorithms and techniques that aim to address three Research Questions (RQs): RQ1: How to achieve accurate and efficient Out-of-Distribution (OOD) detection for DNNs in RTE systems? RQ2: How to predict the performance of DNNs under continuous distribution shifts? RQ3: How to achieve efficient inference of Deep Reinforcement Learning (DRL) agents in RTE systems?

For RQ1, we present a framework for OOD detection based on outlier detection in one or more hidden layers of a DNN with either Isolation Forest (IF) or Local Outlier Factor (LOF). We also perform a comprehensive and systematic benchmark study of multiple well-known OOD detection algorithms in terms of both accuracy and execution time on different hardware platforms, in order to provide a useful reference for the practical deployment of OOD detection algorithms in RTE systems. For RQ2, we present a framework for predicting the performance of DNNs for end-to-end Autonomous Driving under continuous distribution shifts with two approaches: using an Autoencoder that attempts to reconstruct the input image; and applying Anomaly Detection algorithms to the hidden layer(s) of the DNN. For RQ3, we present a framework for model compression of the policy network of a DRL agent for deployment in RTE systems by leveraging the relevance scores computed by Layer-wise Relevance Propagation (LRP) to rank and prune the convolutional filters, combined with fine-tuning using policy distillation.

The algorithms and techniques developed in this thesis have been evaluated on standard datasets and benchmarks. To summarize our findings, we have developed novel OOD detection algorithms with high accuracy and efficiency; identified OOD detection algorithms with relatively high accuracy and low execution times through benchmarking; developed a framework for DNN performance prediction under continuous distribution shifts, and identified most effective Anomaly Detection algorithms for use in the framework; developed a framework for model compression of DRL agents that is effective in reducing model size and inference time for deployment in RTE systems. The research results are expected to assist system designers in the task of safe and efficient application of DNNs in resource-constrained RTE systems.

Ort, förlag, år, upplaga, sidor
Umeå: Umeå University , 2023. , s. 49
Nyckelord [en]
Machine Learning/Deep Learning, Real-Time Embedded systems, Out-of-Distribution Detection, Distribution Shifts, Deep Reinforcement Learning, Model Compression, Policy Distillation.
Nationell ämneskategori
Datavetenskap (datalogi)
Identifikatorer
URN: urn:nbn:se:umu:diva-214365ISBN: 978-91-8070-161-7 (digital)ISBN: 978-91-8070-160-0 (tryckt)OAI: oai:DiVA.org:umu-214365DiVA, id: diva2:1796499
Disputation
2023-10-09, Triple Helix, Samverkanshuset, Umeå, 13:00 (Engelska)
Opponent
Handledare
Tillgänglig från: 2023-09-18 Skapad: 2023-09-12 Senast uppdaterad: 2023-09-13Bibliografiskt granskad
Delarbeten
1. Out-of-Distribution Detection for Deep Neural Networks with Isolation Forest and Local Outlier Factor
Öppna denna publikation i ny flik eller fönster >>Out-of-Distribution Detection for Deep Neural Networks with Isolation Forest and Local Outlier Factor
Visa övriga...
2021 (Engelska)Ingår i: IEEE Access, E-ISSN 2169-3536, Vol. 9, s. 132980-132989Artikel i tidskrift (Refereegranskat) Published
Abstract [en]

Deep Neural Networks (DNNs) are extensively deployed in today's safety-critical autonomous systems thanks to their excellent performance. However, they are known to make mistakes unpredictably, e.g., a DNN may misclassify an object if it is used for perception, or issue unsafe control commands if it is used for planning and control. One common cause for such unpredictable mistakes is Out-of-Distribution (OOD) input samples, i.e., samples that fall outside of the distribution of the training dataset. We present a framework for OOD detection based on outlier detection in one or more hidden layers of a DNN with a runtime monitor based on either Isolation Forest (IF) or Local Outlier Factor (LOF). Performance evaluation indicates that LOF is a promising method in terms of both the Machine Learning metrics of precision, recall, F1 score and accuracy, as well as computational efficiency during testing.

Ort, förlag, år, upplaga, sidor
Institute of Electrical and Electronics Engineers (IEEE), 2021
Nyckelord
deep neural networks, isolation forest, local outlier factor, Out-of-distribution, outlier detection, runtime monitoring
Nationell ämneskategori
Datavetenskap (datalogi) Datorsystem
Identifikatorer
urn:nbn:se:umu:diva-191334 (URN)10.1109/ACCESS.2021.3108451 (DOI)000702542000001 ()2-s2.0-85113855730 (Scopus ID)
Tillgänglig från: 2022-01-13 Skapad: 2022-01-13 Senast uppdaterad: 2023-09-12Bibliografiskt granskad
2. Timing performance benchmarking of out-of-distribution detection algorithms
Öppna denna publikation i ny flik eller fönster >>Timing performance benchmarking of out-of-distribution detection algorithms
Visa övriga...
2023 (Engelska)Ingår i: Journal of Signal Processing Systems, ISSN 1939-8018, E-ISSN 1939-8115Artikel i tidskrift (Refereegranskat) Epub ahead of print
Abstract [en]

In an open world with a long-tail distribution of input samples, Deep Neural Networks (DNNs) may make unpredictable mistakes for Out-of-Distribution (OOD) inputs at test time, despite high levels of accuracy obtained during model training. OOD detection can be an effective runtime assurance mechanism for safe deployment of machine learning algorithms in safety–critical applications such as medical imaging and autonomous driving. A large number of OOD detection algorithms have been proposed in recent years, with a wide range of performance metrics in terms of accuracy and execution time. For real-time safety–critical applications, e.g., autonomous driving, timing performance is of great importance in addition to accuracy. We perform a comprehensive and systematic benchmark study of multiple OOD detection algorithms in terms of both accuracy and execution time on different hardware platforms, including a powerful workstation and a resource-constrained embedded device, equipped with both CPU and GPU. We also profile and analyze the internal details of each algorithm to identify the performance bottlenecks and potential for GPU acceleration. This paper aims to provide a useful reference for the practical deployment of OOD detection algorithms for real-time safety–critical applications.

Ort, förlag, år, upplaga, sidor
Springer-Verlag New York, 2023
Nyckelord
Deep Learning, Embedded systems, Machine Learning, Out-of-Distribution detection, Real-time systems
Nationell ämneskategori
Datavetenskap (datalogi)
Identifikatorer
urn:nbn:se:umu:diva-206357 (URN)10.1007/s11265-023-01852-0 (DOI)000955519800001 ()2-s2.0-85150652364 (Scopus ID)
Tillgänglig från: 2023-04-26 Skapad: 2023-04-26 Senast uppdaterad: 2023-09-12
3. Efficient performance prediction of end-to-end autonomous driving under continuous distribution shifts based on anomaly detection
Öppna denna publikation i ny flik eller fönster >>Efficient performance prediction of end-to-end autonomous driving under continuous distribution shifts based on anomaly detection
2023 (Engelska)Ingår i: Journal of Signal Processing Systems, ISSN 1939-8018, E-ISSN 1939-8115Artikel i tidskrift (Refereegranskat) Epub ahead of print
Abstract [en]

A Deep Neural Network (DNN)’s prediction may be unreliable outside of its training distribution despite high levels of accuracy obtained during model training. The DNN may experience different degrees of accuracy degradation for different levels of distribution shifts, hence it is important to predict its performance (accuracy) under distribution shifts. In this paper, we consider the end-to-end approach to autonomous driving of using a DNN to map from an input image to the control action such as the steering angle. For each input image with possible perturbations that cause distribution shifts, we design a Performance Prediction Module to compute its anomaly score, and use it to predict the DNN’s expected prediction error, i.e., its expected deviation from the ground truth (optimal) control action, which is not available after deployment. If the expected prediction error is too large, then the DNN’s prediction may no longer be trusted, and remedial actions should be taken to ensure safety. We consider different methods for computing the anomaly score for the input image, including using the reconstruction error of an Autoencoder, or applying an Anomaly Detection algorithm to a hidden layer of the DNN. We present performance evaluation of the different methods in terms of both prediction accuracy and execution time on different hardware platforms, in order to provide a useful reference for the designer to choose among the different methods.

Ort, förlag, år, upplaga, sidor
Springer, 2023
Nyckelord
Machine learning, Deep learning, Distribution shifts, Performance prediction, End-to-end autonomous driving
Nationell ämneskategori
Datavetenskap (datalogi)
Identifikatorer
urn:nbn:se:umu:diva-214350 (URN)10.1007/s11265-023-01893-5 (DOI)2-s2.0-85177063760 (Scopus ID)
Forskningsfinansiär
Kempestiftelserna
Anmärkning

Originally included in thesis in manuscript form. 

Tillgänglig från: 2023-09-12 Skapad: 2023-09-12 Senast uppdaterad: 2023-12-04
4. LRP-based network pruning and policy distillation of robust and non-robust DRL agents for embedded systems
Öppna denna publikation i ny flik eller fönster >>LRP-based network pruning and policy distillation of robust and non-robust DRL agents for embedded systems
Visa övriga...
2023 (Engelska)Ingår i: Concurrency and Computation, ISSN 1532-0626, E-ISSN 1532-0634, Vol. 35, nr 19, artikel-id e7351Artikel i tidskrift (Refereegranskat) Published
Abstract [en]

Reinforcement learning (RL) is an effective approach to developing control policies by maximizing the agent's reward. Deep reinforcement learning uses deep neural networks (DNNs) for function approximation in RL, and has achieved tremendous success in recent years. Large DNNs often incur significant memory size and computational overheads, which may impede their deployment into resource-constrained embedded systems. For deployment of a trained RL agent on embedded systems, it is necessary to compress the policy network of the RL agent to improve its memory and computation efficiency. In this article, we perform model compression of the policy network of an RL agent by leveraging the relevance scores computed by layer-wise relevance propagation (LRP), a technique for Explainable AI (XAI), to rank and prune the convolutional filters in the policy network, combined with fine-tuning with policy distillation. Performance evaluation based on several Atari games indicates that our proposed approach is effective in reducing model size and inference time of RL agents. We also consider robust RL agents trained with RADIAL-RL versus standard RL agents, and show that a robust RL agent can achieve better performance (higher average reward) after pruning than a standard RL agent for different attack strengths and pruning rates.

Ort, förlag, år, upplaga, sidor
John Wiley & Sons, 2023
Nyckelord
embedded systems, knowledge distillation, policy distillation, reinforcement learning
Nationell ämneskategori
Datavetenskap (datalogi)
Identifikatorer
urn:nbn:se:umu:diva-200565 (URN)10.1002/cpe.7351 (DOI)000868806400001 ()2-s2.0-85139981238 (Scopus ID)
Anmärkning

Special Issue. 

First published online October 2022.

Tillgänglig från: 2022-12-01 Skapad: 2022-12-01 Senast uppdaterad: 2023-11-09Bibliografiskt granskad

Open Access i DiVA

fulltext(1214 kB)125 nedladdningar
Filinformation
Filnamn FULLTEXT01.pdfFilstorlek 1214 kBChecksumma SHA-512
517f4cdc82ab8ab92282b23ba0ecffad418f814fc30ac86942db3f460686f5d2a391ce61857fddf0a4a559366b2ea3ebcca1d45f8e23d12df09c0105c6f73c52
Typ fulltextMimetyp application/pdf
spikblad(130 kB)29 nedladdningar
Filinformation
Filnamn SPIKBLAD01.pdfFilstorlek 130 kBChecksumma SHA-512
3ae4bc2017214b922ee9b8f9d0f44176fded343a83f987cb935bfa89635665ccb9b400335632b1db05e6863236bffce58d749685df35fcf51ae11b1769e5daa5
Typ spikbladMimetyp application/pdf

Person

Luan, Siyu

Sök vidare i DiVA

Av författaren/redaktören
Luan, Siyu
Av organisationen
Institutionen för tillämpad fysik och elektronik
Datavetenskap (datalogi)

Sök vidare utanför DiVA

GoogleGoogle Scholar
Totalt: 125 nedladdningar
Antalet nedladdningar är summan av nedladdningar för alla fulltexter. Det kan inkludera t.ex tidigare versioner som nu inte längre är tillgängliga.

isbn
urn-nbn

Altmetricpoäng

isbn
urn-nbn
Totalt: 804 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf