About
Pietro Barbiero is a computational scientist and researcher at the University of Cambridge with over three years of expertise in machine learning, neural networks, and evolutionary algorithms, particularly in precision medicine. His work integrates advanced AI methods with mathematical modeling to address complex challenges in healthcare and computational sciences. Currently pursuing a Doctor of Philosophy (Ph.D.) in Artificial Intelligence at the University of Cambridge, Pietro has been actively involved as a Research Assistant since August 2020. His academic journey also includes a Master of Engineering (MEng) in Mathematical Engineering from Politecnico di Torino, showcasing his strong foundation in quantitative disciplines. Pietro's contributions at Cambridge are centered on innovative projects such as the "Digital Patient." This groundbreaking initiative focuses on developing a "digital twin" of patients, combining AI techniques with mathematical modeling to create comprehensive frameworks for predicting and monitoring physiological conditions. This project has the potential to revolutionize personalized medicine by enabling real-time diagnostics and tailored treatment plans. Another notable endeavor, "Deep Competitive Learning," highlights Pietro’s work in enhancing unsupervised learning techniques. By creating gradient-based competitive layers for integration with deep learning models, he has advanced the capabilities of AI systems to tackle unstructured data effectively. These projects reflect Pietro’s commitment to pushing the boundaries of AI research and its practical applications. Pietro’s professional experience includes a stint as an Algorithm Developer at S.d.O Servizi di Organizzazione in Italy, where he honed his skills in computational algorithms and software development. This blend of academic rigor and industry exposure positions him uniquely to bridge theoretical concepts with real-world implementations. His proficiency spans an array of technical domains, including Artificial Intelligence, Machine Learning, and Neural Networks. Endorsed for his skills, Pietro's expertise is evident in his ability to design and execute complex AI-driven solutions. He has a collaborative ethos, evident from his involvement in interdisciplinary projects and his engagement with the academic community. Pietro’s work has garnered attention for its innovation and potential to transform sectors such as healthcare and data science. With his dedication to advancing the frontiers of AI and a proven track record of impactful research, he continues to make significant strides in the realm of computational science.
View More >>Skills
Experience
Publication
-
December, 2024
From Charts to Atlas: Merging Latent Spaces into One
Models trained on semantically related datasets and tasks exhibit comparable inter-sample relations within their latent spaces. We investigate in this study the aggregation of such latent sp...
-
September, 2023
Categorical Foundations of Explainable AI: A Unifying Theory
Explainable AI (XAI) aims to address the human need for safe and reliable AI systems. However, numerous surveys emphasize the absence of a sound mathematical formalization of key XAI notions...
-
July, 2023
Bridging Equational Properties and Patterns on Graphs: an AI-Based Approach
Journal : Proceedings of Machine Learning Research
AI-assisted solutions have recently proven successful when applied to Mathematics and have opened new possibilities for exploring unsolved problems that have eluded traditional approaches fo...
-
July, 2023
SHARCS: Shared Concept Space for Explainable Multimodal Learning
Multimodal learning is an essential paradigm for addressing complex real-world problems, where individual data modalities are typically insufficient to accurately solve a given modelling tas...
-
May, 2023
Interpretable Graph Networks Formulate Universal Algebra Conjectures
The rise of Artificial Intelligence (AI) recently empowered researchers to investigate hard mathematical problems which eluded traditional approaches for decades. Yet, the use of AI in Unive...
-
April, 2023
Global Explainability of GNNs via Logic Combination of Learned Concepts
While instance-level explanation of GNN is a well-studied problem with plenty of approaches being developed, providing a global explanation for the behaviour of a GNN is much less explored, ...
-
February, 2023
GCI: A Graph Concept Interpretation Framework
Explainable AI (XAI) underwent a recent surge in research on concept extraction, focusing on extracting human-interpretable concepts from Deep Neural Networks. An important challenge facing ...
-
January, 2023
Logic Explained Networks
Journal : Artificial Intelligence 1872-7921
The large and still increasing popularity of deep learning clashes with a major limit of neural network architectures, that consists in their lack of capability in providing human-understand...
-
January, 2023
Extending Logic Explained Networks to Text Classification
Recently, Logic Explained Networks (LENs) have been proposed as explainable-by-design neural models providing logic explanations for their predictions. However, these models have only been a...
-
December, 2022
Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off
Deploying AI-powered systems requires trustworthy models supporting effective human interactions, going beyond raw prediction accuracy. Concept bottleneck models promote trustworthiness by c...
Scholar9 Profile ID
S9-122024-2007269

Publication
(13)

Article Reviewed
(0)

Citations
(0)

Network
(2)

Conferences/Seminar
(0)