PhD Position F/M Workflow Provenance and Its Application to Explainable and Transparent Artificial Intelligence

il y a 4 semaines


Rennes, Bretagne, France INRIA Temps plein
Job Description

We are seeking a highly motivated and talented PhD student to join our team at INRIA to work on a project focused on workflow provenance for explainable and transparent artificial intelligence. The successful candidate will have the opportunity to contribute to the development of novel methods and tools for capturing, analyzing, and visualizing workflow provenance data, with a focus on explainability and transparency in AI systems.

Research Objectives

The project aims to advance the research on AI's transparency and explainability, addressing the growing concerns about ethical and practical implications of AI applications. The PhD student will investigate mechanisms to formalize, capture, store, and manage metadata in AI-powered workflows, and will explore the relationship between model provenance, metadata, and model behavior, aiming to decipher how architectural and algorithmic characteristics impact in the model's outcome.

Methodology

The PhD student will start by analyzing our collection of neural network record trails under the light of the new taxonomy from Aim A. In these previous work we amassed and annotated the life-cycle of 6,000 randomly-generated NNs across their generation, training, and validation stages. The resultant record trails, comprising both structural and learning curve data, were systematically organized in tabular text files. These record trails constitute a valuable curated collection of provenance information encompassing architecture, metadata, and performance metrics. In a similar approach to our previous work, we plan to generate record trails from foundation models, and we will enrich them with comprehensive metadata captured using the proof-of-concept from Aim B. We will apply causal inference techniques on the taxonomy-structured metadata to understand the feature strength on these data and the causal relationships between the architectural features (e.g., hyperparameters, number of layers, type of layers), behavioral features (e.g., final accuracy, accuracy curve) and other elements mapped to the taxonomies from Aim A.

Requirements

The successful candidate will have a strong academic record in computer science courses, knowledge on distributed systems and data management systems, strong programming skills (Python, C/C++), ability and motivation to conduct high-quality research, including publishing the results in relevant venues, very good communication skills in oral and written English, open-mindedness, strong integration skills and team spirit. Knowledge on machine learning and data analysis methods, professional experience in the areas of HPC and Big Data management are appreciated.

Benefits

The PhD student will benefit from a monthly gross salary amounting to 2100 euros for the first and second years and 2190 euros for the third year, subsidized meals, partial reimbursement of public transport costs, possibility of teleworking (90 days per year) and flexible organization of working hours, partial payment of insurance costs.



  • Rennes, Bretagne, France INRIA Temps plein

    Job DescriptionINRIA is seeking a highly motivated PhD researcher to join our team and contribute to the development of workflow provenance for explainable and transparent artificial intelligence.Context and OverviewArtificial intelligence (AI) is driving scientific discovery and economic growth in various application domains, but its pervasive presence...


  • Rennes, Bretagne, France INRIA Temps plein

    Job DescriptionINRIA is seeking a highly motivated PhD researcher to join our team and contribute to the advancement of explainable and transparent artificial intelligence (AI) through workflow provenance research.Context and OverviewArtificial intelligence is driving scientific discovery and economic growth in various application domains, but its pervasive...


  • Rennes, Bretagne, France INRIA Temps plein

    Research Position in Workflow Provenance and Explainable AIThe KerData team at Inria is seeking a highly motivated PhD researcher to work on a project focused on workflow provenance and explainable AI. The successful candidate will contribute to advancing the research on AI transparency and explainability, addressing the growing concerns about ethical and...


  • Rennes, Bretagne, France INRIA Temps plein

    Job DescriptionWe are seeking a highly motivated PhD researcher to join our team at INRIA and contribute to the development of workflow provenance and explainable artificial intelligence. The successful candidate will work under the supervision of a team of experienced researchers and will have the opportunity to collaborate with international...


  • Rennes, Bretagne, France INRIA Temps plein

    Research Position in Artificial Intelligence Transparency and ExplainabilityThe KerData team at INRIA is seeking a highly motivated PhD candidate to work on a research project focused on advancing the transparency and explainability of Artificial Intelligence (AI) systems. The project aims to investigate mechanisms to formalize, capture, store, and manage...


  • Rennes, Bretagne, France INRIA Temps plein

    Context and OverviewArtificial Intelligence (AI) is driving scientific discovery and economic growth in various application domains, impacting routine daily tasks to societal-level challenges. However, research communities, industry players, and social actors express increasing concern about the potential ethical and practical implications of AI. To address...


  • Rennes, Bretagne, France INRIA Temps plein

    Context and OverviewArtificial Intelligence (AI) is driving scientific discovery and economic growth in various application domains, impacting from routine daily tasks to societal-level challenges. However, research communities, industry players, and social actors are expressing increasing concern about the potential ethical and practical implications of the...


  • Rennes, Bretagne, France INRIA Temps plein

    Context and OverviewArtificial Intelligence (AI) is driving scientific discovery and economic growth in various application domains, impacting routine daily tasks to societal-level challenges. However, research communities, industry players, and social actors express increasing concern about the potential ethical and practical implications of AI. To address...


  • Rennes, Bretagne, France INRIA Temps plein

    Research Position in AI Transparency and ExplainabilityThe KerData team at INRIA is seeking a highly motivated PhD candidate to contribute to the advancement of AI transparency and explainability. The successful candidate will work on the development of mechanisms to formalize, capture, store, and manage metadata in AI-powered workflows.Research...


  • Rennes, Bretagne, France INRIA Temps plein

    Context and OverviewArtificial Intelligence (AI) is driving scientific discovery and economic growth in various application domains, impacting routine daily tasks to societal-level challenges. However, research communities, industry players, and social actors express increasing concern about the potential ethical and practical implications of AI. To address...


  • Rennes, Bretagne, France INRIA Temps plein

    Context and BackgroundWith the increasing need to distribute Artificial Intelligence (AI) applications from the cloud to edge devices, there is a growing trend to design custom and embedded AI Hardware architectures (AI-HW) to support energy-intensive data movement, speed of computation, and large memory resources that AI requires to achieve its full...


  • Rennes, Bretagne, France Inria Temps plein

    PhD Position in Trustworthy AI Hardware ArchitecturesAbout the Research CentreInria Rennes - Bretagne Atlantique Centre is one of Inria's eight centres and has more than thirty research teams. The Inria Centre is a major and recognized player in the field of digital sciences.Research ContextBackground and ContextThere is a growing need to distribute...


  • Rennes, Bretagne, France Inria Temps plein

    About the Centre or DepartmentInria Rennes - Bretagne Atlantique Centre is one of Inria's eight centres and has more than thirty research teams. The Inria Centre 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...


  • Rennes, Bretagne, France INRIA Temps plein

    Context and Background:As the field of Artificial Intelligence (AI) continues to advance, the need to distribute AI applications from the cloud to edge devices has become increasingly important. This trend aims to address issues related to data privacy, bandwidth limitations, power consumption reduction, and low latency requirements, particularly in...


  • Rennes, Bretagne, France INRIA Temps plein

    Context and BackgroundThe increasing need to distribute Artificial Intelligence (AI) applications from the cloud to edge devices has led to a growing trend of designing custom and embedded AI Hardware architectures (AI-HW) to support energy-intensive data movement, speed of computation, and large memory resources that AI requires to achieve its full...


  • Rennes, Bretagne, France INRIA Temps plein

    Context and BackgroundAs the demand for Artificial Intelligence (AI) applications grows, there is an increasing need to distribute AI applications from the cloud to edge devices. This trend aims to address issues related to data privacy, bandwidth limitations, power consumption reduction, and low latency requirements, especially for real-time, mission- and...


  • Rennes, Bretagne, France INRIA Temps plein

    Context and ObjectivesThis PhD thesis is part of the NumPEx project, a key national initiative aiming to co-design the software stack for the exascale era and prepare applications accordingly. The thesis will be co-supervised by Inria and CEA, with collaborations expected within the consortium.Research TeamThe thesis will be hosted by the KerData team at the...


  • Rennes, Bretagne, France INRIA Temps plein

    Context and BackgroundThe increasing need to distribute Artificial Intelligence (AI) applications from the cloud to edge devices has led to a growing trend of designing custom and embedded AI Hardware architectures (AI-HW) to support energy-intensive data movement, speed of computation, and large memory resources that AI requires to achieve its full...


  • Rennes, Bretagne, France INRIA Temps plein

    Context and ObjectivesThis PhD thesis is part of the NumPEx project, a key national initiative aiming to co-design the software stack for the exascale era and prepare applications accordingly. The thesis will be co-supervised by Inria and CEA, with collaborations expected within the NumPEx consortium.Research TeamThe thesis will be hosted by the KerData team...


  • Rennes, Bretagne, France INRIA Temps plein

    Context and ObjectivesDeep Neural Networks (DNNs) are widely used predictive models in machine learning, but they require significant energy and resources. To address this, custom Artificial Intelligence (AI) hardware accelerators are being designed to support DNNs. However, these accelerators are prone to hardware faults (HW faults) that can cause...