About this role
Summary: This internship involves investigating and implementing abductive explanations and concept-based decision procedures within the CaBRNet library. The role focuses on designing proof-of-concept models, evaluating them against existing metrics, and contributing to potential scientific publications in a research environ...
### Sujet de stage
Case-based reasoning is a popular framework for explainable AI. It exposes the
network decision process by relating inference-time inputs with
prototypes.
Recent work proposed to rely on the formalism of Abductive Explanations as to
guarantee that an prototype-based explanation is both minimal and sufficient.
Assigning meaning to prototypes is however a time-consuming task, as the various models tend to learn prototypes that do not carry sufficiently high-level meaning.
A parallel line of work is that of Concept Learning. By injecting concepts
meaningful to human operators, Concept Bottleneck Models
provide a principled way to map feature maps to annotated concepts, providing an
easy to understand - and contest - decision procedure.
Recent work display a renewed interest in those approaches, by exposing counterfactuals generation capabilities.
### Description de l'offre
As an intern at the CEA, you will have the opportunity to work in a world-renowned research environment. Our teams consist of passionate and dedicated experts, providing an environment conducive to learning and collaboration. You will have access to state-of-the-art equipment and top-tier research resources to carry out your assignments. The work performed may potentially lead to a scientific publication.
Context :
The main objective of the internship is to investigate, design and implement an
abductive explanations and
concept-based decision procedure.
What do we expect from you ?
The broad internship goals are:
- familiarization with the state-of-the-art;
- sketching a decision procedure on paper;
- implement a proof-of-concept of concept bottleneck models in the CaBRNet
library;
- evaluate the approach on existing metrics and various human-in-the-loop
evaluation methods.
#*Cea List*
### Profil du candidat
Profile :
##### Minimal qualifications
- master student or equivalent (2nd/3rd engineering school year) in computer
science and/or machine learning;
- some knowledge of the Python programming language;
- ability to work in a team;
##### Preferred
- knowledge of the PyTorch framework;
- used to work with version control systems (git) and software forges (GitLab);
- background on explainable AI;