Analysis and improvement of resilience for long short-term memory neural networksAhmadilivani, Mohammad Hasan; Raik, Jaan; Daneshtalab, Masoud; Kuusik, Alar2023 IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFT)2023 / 4 p https://doi.org/10.1109/DFT59622.2023.10313559

APPRAISER : DNN fault resilience analysis employing approximation errorsTaheri, Mahdi; Ahmadilivani, Mohammad Hasan; Jenihhin, Maksim; Daneshtalab, Masoud; Raik, Jaan2023 26th International Symposium on Design and Diagnostics of Electronic Circuits and Systems (DDECS)2023 / p. 124−127 : ill https://ddecs2023.taltech.ee/ https://doi.org//10.1109/DDECS57882.2023.10139468

Assessment and Enhancement of Hardware Reliability for Deep Neural Networks = Riistvara töökindluse hindamine ja täiustamine süvanärvivõrkude jaoksAhmadilivani, Mohammad Hasan2025 https://www.ester.ee/record=b5739227*est https://digikogu.taltech.ee/et/Item/652d50e3-773f-4de5-897d-86531feb0d56 https://doi.org/10.23658/taltech.19/2025

Cost-effective fault tolerance for CNNs using parameter vulnerability based hardening and pruningAhmadilivani, Mohammad Hasan; Mousavi, Seyedhamidreza; Raik, Jaan; Daneshtalab, Masoud; Jenihhin, Maksim2024 IEEE 30th International Symposium on On-line Testing and Robust System Design (IOLTS) : IOLTS 2024 : July 03rd-05th 2024, Rennes, Brittany, France2024 / 7 p https://doi.org/10.1109/IOLTS60994.2024.10616072 Article at Scopus Article at WOS

DeepAxe : a framework for exploration of approximation and reliability trade-offs in DNN acceleratorsTaheri, Mahdi; Riazati, Mohamad; Ahmadilivani, Mohammad Hasan; Jenihhin, Maksim; Daneshtalab, Masoud; Raik, Jaan; Sjödin, Mikael; Lisper, Björn2023 24th International Symposium on Quality Electronic Design (ISQED)2023 / 8 p. : ill https://doi.org/10.1109/ISQED57927.2023.10129353

DeepVigor: VulnerabIlity Value RanGes and FactORs for DNNs’ Reliability AssessmentAhmadilivani, Mohammad Hasan; Taheri, Mahdi; Raik, Jaan; Daneshtalab, Masoud; Jenihhin, MaksimIEEE European Test Symposium (ETS) : Venice, Italy, 22-26 May 2023 : proceedings2023 / 6 p. : ill https://doi.org/10.1109/ETS56758.2023.10174133

DeepVigor+: Scalable and Accurate Semi-Analytical Fault Resilience Analysis for Deep Neural NetworksAhmadilivani, Mohammad Hasan; Raik, Jaan; Daneshtalab, Masoud; Jenihhin, MaksimarXiv.org2024 / 14 p. : ill https://doi.org/10.48550/arXiv.2410.15742

ECS an endeavor towards providing similar cache reliability behavior in different programsAhmadilivani, Mohammad Hasan; Jahromi, Mohammad Moeini; Salehi, Mostafa E.; Kargar, MonaMicroelectronics Reliability2024 / art. 115295 https://doi.org/10.1016/j.microrel.2023.115295 Journal metrics at Scopus Article at Scopus Journal metrics at WOS Article at WOS

An efficient analog convolutional neural network hardware accelerator enabled by a novel memoryless architecture for insect-sized robotsDadras, Iman; Ahmadilivani, Mohammad Hasan; Banerji, Saoni; Raik, Jaan; Abloo, Alvo2022 11th International Conference on Modern Circuits and Systems Technologies (MOCAST) : Bremen, Germany : 08-10 June 20222022 / p. 1-6 https://doi.org/10.1109/MOCAST54814.2022.9837551

Enhancing fault resilience of QNNs by selective neuron splittingAhmadilivani, Mohammad Hasan; Taheri, Mahdi; Raik, Jaan; Daneshtalab, Masoud; Jenihhin, Maksim2023 IEEE 5th International Conference on Artificial Intelligence Circuits and Systems (AICAS)2023 / 5 p. : ill https://doi.org/10.1109/AICAS57966.2023.10168633

Fully-fusible convolutional neural networks for end-to-end fused architecture with FPGA implementationDadras, Iman; Seydi, Sakineh; Ahmadilivani, Mohammad Hasan; Raik, Jaan; Salehi, Mostafa E.2023 30th IEEE International Conference on Electronics, Circuits and Systems (ICECS)2023 / 5 p. https://doi.org/10.1109/ICECS58634.2023.10382831

Heterogeneous Approximation of DNN HW Accelerators based on Channels VulnerabilityCherezova, Natalia; Pappalardo, Salvatore; Taheri, Mahdi; Ahmadilivani, Mohammad Hasan; Deveautour, Bastien; Bosio, Alberto; Raik, Jaan; Jenihhin, Maksim2024 IFIP/IEEE 32nd International Conference on Very Large Scale Integration (VLSI-SoC)2024 / 4 p. : ill https://doi.org//10.1109/VLSI-SoC62099.2024.10767798

Keynote: cost-efficient reliability for Edge-AI chipsJenihhin, Maksim; Taheri, Mahdi; Cherezova, Natalia; Ahmadilivani, Mohammad Hasan; Selg, Hardi; Jutman, Artur; Shibin, Konstantin; Tsertov, Anton; Devadze, Sergei; Kodamanchili, Rama Mounika; Rafiq, Ahsan; Raik, Jaan; Daneshtalab, Masoud2024 IEEE 25th Latin American Test Symposium (LATS)2024 / 2 p https://doi.org/10.1109/LATS62223.2024.10534610 Article at Scopus

Machine vision for automated collaborative robot programming in manufacturing industrial factoriesAhmadilivani, Mohammad Hasan; Karatopuk, Emre; Roots, Marten; Raik, JaanSmart machines and systems at the service of mankind : Abstracts of the 12th annual entrepreneurship and innovation conference2024 / p. 10 https://conference.euas.eu/2024/wp-content/uploads/2024/10/ConferenceProceedings2024-1.pdf https://www.ester.ee/record=b5705417*est

ProAct: Progressive Training for Hybrid Clipped Activation Function to Enhance Resilience of DNNsMousavi, Seyedhamidreza; Ahmadilivani, Mohammad Hasan; Raik, Jaan; Jenihhin, Maksim; Daneshtalab, MasoudarXiv.org2024 / 12 p. : ill https://doi.org/10.48550/arXiv.2406.06313

Real-time gait anomaly detection using 1D-CNN and LSTMRostovski, Jakob; Ahmadilivani, Mohammad Hasan; Krivošei, Andrei; Kuusik, Alar; Alam, Muhammad MahtabDigital Health and Wireless Solutions : First Nordic Conference​, NCDHWS 2024, Oulu, Finland, May 7–8, 2024 : Proceedings, Part II2024 / p. 260-278 https://doi.org/10.1007/978-3-031-59091-7_17 Conference proceedings at Scopus Article at Scopus Article at WOS

Special session : approximation and fault resiliency of DNN acceleratorsAhmadilivani, Mohammad Hasan; Barbareschi, Mario; Barone, Salvatore; Bosio, Alberto; Daneshtalab, Masoud; Torca, Salvatore Della; Gavarini, Gabriele; Jenihhin, Maksim; Raik, Jaan; Taheri, Mahdi2023 IEEE 41st VLSI Test Symposium (VTS) : proceedings2023 / 10 p. : ill https://doi.org/10.1109/VTS56346.2023.10140043 Conference proceeding at Scopus Article at Scopus Article at WOS

Special session: reliability assessment recipes for DNN acceleratorsAhmadilivani, Mohammad Hasan; Bosio, Alberto; Deveautour, Bastien; Dos Santos, Fernando Fernandes; Guerrero-Balaguera, Juan-David; Jenihhin, Maksim; Kritikakou, Angeliki; Sierra, Robert Limas; Raik, Jaan; Taheri, Mahdi42nd IEEE VLSI Test Symposium, VTS 20242024 / 11 p. : ill https://doi.org/10.1109/VTS60656.2024.10538707 Conference proceedings at Scopus Article at Scopus Article at WOS

A systematic literature review on hardware reliability assessment methods for deep neural networksAhmadilivani, Mohammad Hasan; Taheri, Mahdi; Raik, Jaan; Daneshtalab, Masoud; Jenihhin, MaksimACM Computing Surveys2024 / art. 141, 39 p. : ill https://doi.org/10.1145/3638242 Journal metrics at Scopus Article at Scopus Journal metrics at WOS Article at WOS

Zero-memory-overhead clipping-based fault tolerance for LSTM deep neural networksParchekani, Bahram; Nazari, Samira; Ahmadilivani, Mohammad Hasan; Azarpeyvand, Ali; Raik, Jaan; Ghasempouri, Tara; Daneshtalab, Masoud37th IEEE International Symposium on Defect and Fault Tolerancein VLSI and Nanotechnology Systems, Harwell, Oxfordshire, Didcot, UK, October 8th - 10th, 20242024 / 4 p. : ill https://doi.org/10.1109/DFT63277.2024.10753533 Conference proceedings at Scopus Article at Scopus