CAMELOT is a CMU|Portugal joint project by Feedzai, CMU, U.Coimbra, IST and FCUL, funded by Lisboa2020, Compete2020 and FEDER.
I am the PI on the FCUL side, coordinating the efforts on verification and automatic optimization of machine learning pipelines.
The CAMELOT (autonomiC plAtform for MachinE Learning using anOnymized daTa) project aims at developing an innovative machine learning platform, which will tackle three key issues that hinder the efficiency and accuracy of modern AI applications:
• Ensuring real-time constraints during both the training and inference phases of machine learning models, while minimizing operational costs deriving from the use of cloud resources.
• Enabling learning over anonymized data, thus circumventing the privacy issues that currently prevent the reuse of information across models trained on datasets belonging to different entities (e.g., different financial institutions).
• Integrating information from different, independent and heterogenous data plataforms (e.g., key-value stores, relational and graph databases) in an automatic approach that maximizes the performance of machine learning applications.
CAMELOT was funded by some FCT, Lisboa2020, Portugal2020 and FEDER:
LISBOA-01-0247-FEDER-045915andPOCI-01-0247-FEDER-045915– Main fundingCPCA/A1/402869/2021– CAMELOT HPC (2021-2022)CPCA/A1/5613/2020– CAMELOT HPC (2020-2021)CPCA/A2/6009/2020– CAMELOT Cloud (2020-2021)
More info
Team
- Alcides Fonseca (PI)
- Antónia Lopes
- Vasco Vasconcelos
- Guilherme Espada (PhD Student)
- Paulo Canelas Santos (PhD Student)
- Catarina Gamboa (PhD Student)
- Pedro Barbosa (PhD Student)
- Máximo Oliveira (MSc Student)
- João David (MSc Student)
- Pedro Silva (MSc Student)
- Leon Ingelse (MSc Student)
- Lukas Abelt (MSc Student)
- Francisco Pimenta (BSc Student)
Software
- GeneticEngine An hybrid of Grammar-Guided and Strongly Typed Genetic Programming in Python.
- Aeon A programming language with liquid types, focused on synthesis
- LiquidJava A library+typechecker + VSCode plugin for Java that adds Liquid Types and TypeState.
Publications
Book Chapters
Journal
- Computational prediction of human deep intronic variation (TBP)
- Clinical significance of genetic variation in hypertrophic cardiomyopathy: comparison of computational tools to prioritize missense variants at Fronteirs in Cardiovascular Medicine
Conference Proceedings
- Domain-Aware Feature Learning with Grammar-Guided Genetic Programming at EuroGP 2023
- Usability-Oriented Design of Liquid Types for Java at ICSE 2023
- Data Types as a More Ergonomic Frontend for Grammar-Guided Genetic Programming at GPCE 2022
- The Usability Argument for Refinement Typed Genetic Programming at PPSN 2022
Workshop Proceedings
- Type Systems in Resource-Aware Programming: Opportunities and Challenges at RAW 2022
- Augmenting Search-based Techniques with Static Synthesis-based Input Generation at SBST 2022
- An Experience Report on Challenges in Learning the Robot Operating System at ROSE 2022
- Figra: evaluating a larger search space for cardumen in automatic program repair at APR 2022
Short Papers
Demos
- Genetic Engine: Genetic Programming for the Common Programmer at <Programming> 2022
- Dive into LiquidJava — Extending Java with Liquid Types at <Programming> 2022
Posters
- Genetic Engine: Grammar-Guided Genetic Programming without the Grammar @ <Programming> 2022
Master Thesis
- Optimization of feature learning through grammar-guided genetic programming by Leon Ingelse
- Improving Machine Learning Pipeline Creation using Visual Programming and Static Analysis by João David
- Exploring a Larger Search Space for Automatic Program Repair by Máximo Oliveira
- LiquidJava: Extending Java with Refinements by Catarina Gamboa
Funding
