Phd Position F/m Reliable Deep Neural Network
Il y a 7 mois
Le descriptif de l’offre ci-dessous est en Anglais_
**Type de contrat **:CDD
**Niveau de diplôme exigé **:Bac + 5 ou équivalent
**Fonction **:Doctorant
**A propos du centre ou de la direction fonctionnelle**:
The Inria Rennes - Bretagne Atlantique Centre is one of Inria's eight centres and has more than thirty research teams. The Inria Center is a major and recognized player in the field of digital sciences. It is at the heart of a rich R&D and innovation ecosystem: highly innovative PMEs, large industrial groups, competitiveness clusters, research and higher education players, laboratories of excellence, technological research institute, etc.
**Contexte et atouts du poste**:
Context & background:
- increasing internet-connected IoTs, and also to alleviate the communication latency, especially for real-time safety-critical decisions, e.g., in autonomous driving.
References:
- [1] Y. LeCun, et al., “Deep learning,” Nature, vol. 521, no. 7553, pp. 436-444, May 2015, doi: 10.1038/nature14539.
[2] B. Moons, et al, “14.5 Envision: A 0.26-to-10TOPS/W subword-parallel dynamic-voltage-accuracy
- frequency
- scalable Convolutional Neural Network processor in 28nm FDSOI,” in IEEE ISSCC, 2017.
[3] C. Torres-Huitzil and B. Girau, “Fault and Error Tolerance in Neural Networks: A Review,” IEEE Access, 2017. [4] A. Lotfi et al., “Resiliency of automotive object detection networks on GPU architectures,” in IEEE ITC, 2019 [5] A. Ruospo, et al., “Investigating data representation for efficient and reliable Convolutional Neural Networks,” in Microprocessors and Microsystems, 2020
[6] F. K. Dosilovic, et al, “Explainable artificial intelligence: A survey,” in MIPRO, 2018.
[7] N. Srivastava et al., “Dropout: A simple way to prevent neural networks from overfitting,” Journal of Machine Learning Research, vol. 15, no. 1, pp. 1929-1958, 2014.
**Mission confiée**:
Ph.D. thesis goal:
- cost selective fault-tolerance strategies; (ii) designing selective fault-tolerance approaches for DNN HW accelerators by using the analysis provided by the fault injection method. The reliability improvements obtained with the above-described methodology will be measured and a design space exploration will be carried out to obtain different DNN HW accelerator implementations providing different trade-offs between fault tolerance and energy efficiency.
**Principales activités**:
More in detail, the Ph.D. student will design and develop a methodology to perform large-scale fault analysis on state-of-the-art DNN hardware architectures. The fault analysis will determine the set of malignant HW faults that mostly impact the accuracy of classification (or other DNN objectives, such as image segmentation) during the inference phase.
DNN inference is known to be very complex, especially on large models and for large datasets. Moreover, in order to obtain statistically relevant metrics about the fault impacts, a large number of faults have to be injected. Since the complexity of fault injection grows linearly with DNN inference complexity and the number of injected faults, the biggest challenge of this task will be to reduce such complexity by proposing statistical or analytical methods to prune the fault space. A first approach is profiling DNN hyper-parameters (e.g. distributions of weight values, neuron activations, arithmetic kernel computations) to determine their sensitivity to the final DNN accuracy. In general, a divide and conquer approach will be designed to reduce the fault injection complexity. “Local” (i.e. at layer/kernel levels) fault injections will be performed, to avoid running the full inference. Then, solid and efficient approaches to link the local sensitivity the global accuracy will be designed and developed.
This will allow realizing an optimized accelerated fault injector framework, enabling large-scale fault simulations. In order to further push the performances and reduce injection time, direct execution of the network (or a portion) on FPGA accelerators can also be leveraged. The enhanced fault-injection framework will allow performing several reliability assessments, such as: (a) training a faulty network to find the fault density beyond which the learning capacity starts degrading; (b) performing inference on a faulty network to be able to identify the set of malignant faults; (c) fault injection during training for passive fault tolerance; (d) fault injection attacks during the inference to evaluate the security fault tolerance can offer.
Finally, error correction mechanisms will be designed, e.g. selective low-precision triplication using checkers/voters, most-significant bits reinforcement, standby sparing and correcting codes; alternatively, if a detection mechanism is available, the re-execution of the task of a faulty component or the dynamic rescheduling/mapping of the DNN to the HW-AI (bypassing faulty components) are viable options. A design space exploration will help
-
Rennes, Bretagne, France Inria Temps pleinOverviewThe Inria Rennes - Bretagne Atlantique Centre is a leading research institution in the field of digital sciences, with over thirty research teams and a strong focus on innovation and technology. Our centre is at the heart of a rich R&D and innovation ecosystem, collaborating with highly innovative PMEs, large industrial groups, competitiveness...
-
PhD Researcher in Fault-Tolerant PIM Accelerators
il y a 4 semaines
Rennes, Bretagne, France Inria Temps pleinJoin Our TeamWe are looking for a talented PhD researcher to join our team at Inria Rennes - Bretagne Atlantique Centre. As a PhD researcher, you will work on the reliability enhancement of post-Von Neumann hardware accelerators, specifically focusing on PIM (Processing-In-Memory) accelerators for deep neural networks (DNNs).About the ProjectThe project aims...
-
PhD Researcher in Reliable Accelerator Design
il y a 1 mois
Rennes, Bretagne, France Inria Temps pleinCompany OverviewInria Rennes - Bretagne Atlantique Centre is a leading research institution in the field of digital sciences, with over thirty research teams and a strong focus on innovation and technology. Our centre is a major player in the rich R&D and innovation ecosystem of northwestern France, working closely with highly innovative SMEs, large...
-
Phd Position F/m Reliability Enhancement of
Il y a 2 mois
Rennes, France Inria Temps pleinLe descriptif de l’offre ci-dessous est en Anglais_ **Type de contrat **:CDD **Niveau de diplôme exigé **:Bac + 5 ou équivalent **Fonction **:Doctorant **A propos du centre ou de la direction fonctionnelle**: The Inria Rennes - Bretagne Atlantique Centre is one of Inria's eight centres and has more than thirty research teams. The Inria Center is a...
-
Phd Position F/m Learning-based Control of An
Il y a 7 mois
Rennes, France Inria Temps pleinLe descriptif de l’offre ci-dessous est en Anglais_ **Type de contrat **:CDD **Niveau de diplôme exigé **:Bac + 5 ou équivalent **Fonction **:Doctorant **A propos du centre ou de la direction fonctionnelle**: The Inria Centre at Rennes University is one of Inria's eight centres and has more than thirty research teams. The Inria Centre is a major and...
-
Phd Position F/m Phd Position F/m Interacting with
Il y a 7 mois
Rennes, France Inria Temps pleinLe descriptif de l’offre ci-dessous est en Anglais_ **Type de contrat **:CDD**Niveau de diplôme exigé **:Bac + 5 ou équivalent**Fonction **:Doctorant**Niveau d'expérience souhaité **:Jeune diplôméA propos du centre ou de la direction fonctionnelle The Inria Centre at Rennes University is one of Inria's eight centres and has more than thirty...
-
Research Engineer in 3D Reconstruction and Neural
Il y a 4 mois
Rennes, France Inria Temps pleinLe descriptif de l’offre ci-dessous est en Anglais_ **Type de contrat **:CDD **Contrat renouvelable **:Oui **Niveau de diplôme exigé **:Bac + 5 ou équivalent **Fonction **:Ingénieur scientifique contractuel **Corps d'accueil **:Ingénieur de Recherche (IR) **A propos du centre ou de la direction fonctionnelle**: The Inria Centre at Rennes...
-
PhD Position F/M in Post-Von Neumann Hardware Accelerators
il y a 4 semaines
Rennes, Bretagne, France Inria Temps pleinAbout the JobAs a PhD researcher, you will be working on enhancing the reliability of post-Von Neumann hardware accelerators. The ideal candidate should have strong knowledge of computer architecture and programming skills in C/C++ and Python.The research team at Inria Rennes - Bretagne Atlantique Centre is seeking a highly motivated individual to work on...
-
Phd Position F/m Machine Learning for Efficient
Il y a 7 mois
Rennes, France Inria Temps pleinLe descriptif de l’offre ci-dessous est en Anglais_ **Type de contrat **:CDD **Niveau de diplôme exigé **:Bac + 5 ou équivalent **Fonction **:Doctorant **A propos du centre ou de la direction fonctionnelle**: The Inria Centre at Rennes University is one of Inria's nine centres and has more than thirty research teams. The Inria Centre is a major and...
-
Reliability Engineer for Advanced Hardware Acceleration
il y a 4 semaines
Rennes, Bretagne, France Inria Temps pleinThe Inria Rennes - Bretagne Atlantique Centre is seeking a highly motivated PhD student to join our team of researchers in the field of digital sciences. Our centre is a major and recognized player in this field, with over thirty research teams and strong connections to leading industrial partners.As a PhD student, you will work on characterizing the...
-
Phd Position F/m Sensors-based Control of An Aerial
Il y a 7 mois
Rennes, France Inria Temps pleinLe descriptif de l’offre ci-dessous est en Anglais_ **Type de contrat **:CDD**Niveau de diplôme exigé **:Bac + 5 ou équivalent**Fonction **:DoctorantA propos du centre ou de la direction fonctionnelle The Inria Centre at Rennes University is one of Inria's eight centres and has more than thirty research teams. The Inria Centre is a major and...
-
Phd Position F/m “haptic Feedback for Supporting
il y a 2 semaines
Rennes, France Inria Temps pleinLe descriptif de l’offre ci-dessous est en Anglais_ **Type de contrat **:CDD **Niveau de diplôme exigé **:Bac + 5 ou équivalent **Fonction **:Doctorant **Niveau d'expérience souhaité **:Jeune diplômé **A propos du centre ou de la direction fonctionnelle**: The Inria Rennes - Bretagne Atlantique Centre is one of Inria's eight centres and has...
-
Phd Position F/m Latency-driven Resources Placement
Il y a 7 mois
Rennes, France Inria Temps pleinLe descriptif de l’offre ci-dessous est en Anglais_ **Type de contrat **:CDD **Niveau de diplôme exigé **:Bac + 5 ou équivalent **Fonction **:Doctorant **A propos du centre ou de la direction fonctionnelle**: The Inria Rennes - Bretagne Atlantique Centre is one of Inria's eight centres and has more than thirty research teams. The Inria Center is a...
-
PhD Position F/M Trustworthy AI hardware architectures
il y a 1 mois
Rennes, France Inria Temps pleinA propos du centre ou de la direction fonctionnelleThe Inria Rennes - Bretagne Atlantique Centre is one of Inria's eight centres and has more than thirty research teams. The Inria Center is a major and recognized player in the field of digital sciences. It is at the heart of a rich R&D and innovation ecosystem: highly innovative PMEs, large industrial...
-
Phd Position at Ietr
Il y a 7 mois
Rennes, France INSA RENNES Temps plein**About us**: INSA Rennes, a founding member of the INSA Group, is the largest public engineering school in Brittany. It welcomes 2,200 students and apprentices and graduates more than 340 engineers, 60 masters and 40 PhDs per year. Composed of 10 teaching departments, including 7 specialties and an apprenticeship program, and supervised by 6 research...
-
Build a Rop Chain Using a Reinforcement Learning
Il y a 3 mois
Rennes, France Quarkslab Temps pleinQuarkslab is a privately held company founded in 2011 with currently more than 100 employees. The company focuses on vulnerability research, reverse engineering and design of security solutions and has developed leading software in the area of threat detection and code/data protection. Quarkslab provides a broad set of products and services based on deep...
-
Phd Position F/m Llm4code and Soprasteria: Software
Il y a 2 mois
Rennes, France Inria Temps pleinLe descriptif de l’offre ci-dessous est en Anglais_ **Type de contrat **:CDD **Niveau de diplôme exigé **:Bac + 5 ou équivalent **Fonction **:Doctorant **A propos du centre ou de la direction fonctionnelle**: The Inria Centre at Rennes University is one of Inria's eight centres and has more than thirty research teams. The Inria centre is a major and...
-
Phd Position F/m Reliability and Security of Large
Il y a 7 mois
Rennes, France Inria Temps pleinLe descriptif de l’offre ci-dessous est en Anglais_ **Type de contrat **:CDD**Niveau de diplôme exigé **:Bac + 5 ou équivalent**Fonction **:DoctorantA propos du centre ou de la direction fonctionnelle The Inria Rennes - Bretagne Atlantique Centre is one of Inria's eight centres and has more than thirty research teams. The Inria Center is a major and...
-
Lead Developper C++
il y a 2 semaines
Rennes, France BEEHIVE SEARCH Temps plein**Notre Client** Notre client, éditeur de logiciels SaaS basé à Rennes, cherche à se renforcer d'un(e) Lead Developper C++. **Missions** Vous managez une équipe de 4 personnes et serez immergé au cœur des algorithmes de contrôle de documents. L'objectif à court terme est de passer d’une architecture monolithique à une architecture distribué...
-
AI HW Fault Tolerance Specialist
il y a 4 semaines
Rennes, Bretagne, France Inria Temps pleinAbout the ProjectThis PhD thesis aims to study the impact of hardware faults not only on AI decisions but also on XAI models. The goal is to design self-explainable, trustworthy, reliable, and real-time verifiable AI hardware accelerators capable of performing self-test, self-diagnosis, and self-correction.Key ActivitiesAnalyze failure mechanisms affecting...
