Titulo Estágio
An architecture for safe machine learning in critical applications
Áreas de especialidade
Engenharia de Software
Sistemas Inteligentes
Local do Estágio
DEI-FCTUC
Enquadramento
This thesis aims to develop an architecture for safe integration of machine learning models in critical applications. In domains such as autonomous vehicles and health care, the safety of the software systems is of great importance. This creates great challenges for artificial intelligence components, namely those based on machine learning.
Machine learning mainly deals with example-based supervised learning algorithms. The result is a model that is difficult to examine and to understand. It can also make mistakes because the specification is a set of examples and new cases not belonging to the set can be seen in the real world. For this reason, this thesis aims to design an architecture to guarantee safety properties of machine learning models, when they are used in a given context.
The thesis shall design an architecture that combines machine learning models with a supervisor that shall monitor the system during its execution. Docker shall be used to make the configuration portable across multiple platforms and the scikit-learn tools shall be used in conjunction with Jupyter Notebook for presentation. A general monitor and associated algorithms shall be developed to support the thesis goals. At the end, it shall be possible do demonstrate and evaluate the architecture on distinct models and datasets.
Objetivo
The thesis has three main goals:
1. Develop an architecture that incorporates an online supervisor to monitor machine learning models during execution.
2. Construct and implement the necessary algorithms for the online monitor and to integrate the architectural components into the machine learning pipeline.
3. Prepare a case study, using at least two datasets, to train the models and run the necessary experiments to comparatively evaluate the results of the proposed architecture.
Plano de Trabalhos - Semestre 1
- State of the art (Months 1 and 2)
The first stage will consist in studying background knowledge on the topics related to the thesis. Namely, knowledge on machine learning, online monitoring and tools such as scikit-learn and docker. At this point, the thesis chapter on the state of the art shall be drafted.
- Preparation of a case study and initial version of the algorithms (Months 3 and 4)
A first machine learning model shall be trained on a public dataset, to be selected. The initial version of the architecture, including a monitoring component, shall be developed. At the end of this stage, it should be possible to demonstrate a first functional prototype of the system.
- Intermediate report (Month 5)
The tasks carried out during the first semester will be documented in the form of an intermediate report, followed by a public presentation and discussion. The most relevant topics at this stage are: context, problem statement, state of the art and preliminary discussion of the solution and its intended objectives.
Plano de Trabalhos - Semestre 2
== Plano de trabalhos Semestre 2 ==
- Development of the architecture and final algorithms (Months 6 and 7)
At this stage the development of the proposed architecture shall be completed, including the implementation of the necessary algorithms for the online monitor. This includes metrics of proximity to decision boundaries and monitoring if particular uses are within parameters with which the model is reliable. The full environment should be usable and ready for evaluation.
- Evaluation of the proposed architecture (Month 8)
The proposed architecture shall be evaluated by applying it to, at least, two distinct machine learning models and two different datasets. The goal is to demonstrate the usefulness and effectiveness of the architecture in handling machine learning errors.
- Master’s thesis (Month 9)
The writing of the master's dissertation must be completed and the respective public presentation prepared. The dissertation must document all the work carried out, proposed solution, the results and the conclusions obtained.
Condições
A research scholarship will be opened to support the student during the period of full-time work.
The work will be carried out at the Department of Informatics Engineering of the University of Coimbra and a place of work will be made available in the laboratories of the DEI as well as the computational resources for carrying out experiments.
Observações
This work is carried out in the context of a research project and there will be the possibility of collaboration with project partners of the University of Coimbra.
Orientador
Raul Barbosa
rbarbosa@dei.uc.pt 📩