An Intelligent Approach to Fruit Inspection: Defect Identification on Plum Surfaces using YOLO-based Model [.pdf]

Interpretable Prediction of Covid-19 Positivity using a Neural-Symbolic Approach [.pdf]

Learning the parameters of deep probabilistic logic programs In Elena Bellodi and Tom Schrijvers, editors, Probabilistic Logic Programming (PLP 2018), volume 2219 of CEUR Workshop Proceedings [.pdf]

Automated Defect Detection and Classification in Cosmetic and Pharmaceutical Bottles Using Neural Networks RiCeRcA Workshop co-located with the 17th International Conference of the Italian Association for Artificial Intelligence (Ai*iA 2018) This work presents a system that utilizes neural networks for extracting and classifying defects in cosmetic and pharmaceutical bottles. The system achieves high accuracy in identifying defects in different classes, such as rubber, aluminum, glass, hair, and tissue. [.pdf]

Deep learning for probabilistic logic programming In Marco Rospocher, Luciano Serafini, and Sara Tonelli, editors, AI*IA 2018 Doctoral Consortium, Proceedings of the AI*IA Doctoral Consortium (DC), volume 2249 of CEUR Workshop Proceedings [.pdf]

Deep probabilistic logic programming In Christian Theil Have and Riccardo Zese, editors, Proceedings of the 4th International Workshop on Probabilistic logic programming, (PLP 2017), volume 1916 of CEUR Workshop Proceedings, pages 3--14, Aachen, Germany, 2017. Sun SITE Central Europe [.pdf]

Revolutionizing African Agriculture: A Deep Learning Approach for Quality Assessment of African Pears Using Artificial Intelligence to empower digital economy in the North Cameroon, INDABAX CAMEROON, 24-26 June 2024, Institute of Fine Arts & Innovation, University of Garoua  [.pdf]

Intelligent Fruit Inspection System: Developing a YOLO-based Model for Identifying Defects on Plums Surface NeurIPS 2023: Conference on Neural Information Processing Systems, New Orleans Ernest N. Morial Convention Center, USA [.pdf]

Learning Hierarchical Probabilistic Logic Programs 1st International Joint Conference on Learning & Reasoning - IJCLR 2021 [.pdf]

Lifted discriminative learning of probabilistic logic programs In Nicolas Lachiche and Christel Vrain, editors, 27th International Conference on Inductive Logic Programming, ILP 2017, 2017

Neurosymbolic AI: Bridging Deep Learning and Probabilistic Logic Rules Abstract: The talk explores the integration of Neurosymbolic AI, a paradigm that merges deep learning (sub-symbolic) with probabilistic logic programming (symbolic reasoning). The objective is to leverage the scalability and pattern recognition abilities of neural networks while incorporating the interpretability and structured knowledge of symbolic AI. The discussion begins by introducing Probabilistic Logic Programming (PLP) and its application in representing uncertain knowledge. Key tasks such as inference, parameter learning, and structure learning are explored, showcasing how probabilistic reasoning can be systematically applied to structured data. Building upon PLP, the talk presents Lifted Probabilistic Logic Programming (LPLP), which enhances efficiency by reasoning over groups of entities rather than individuals. Then Hierarchical Probabilistic Logic Programming (HPLP), a structured framework that introduces multiple layers of abstraction in probabilistic logic programs, enabling more complex knowledge representation. HPLP can be converted into Deep neural Networks bridging the gap between Neural and symbolic AI. Practical applications of Neurosymbolic AI in healthcare are discussed, including predicting critical COVID-19 conditions through a hybrid model that combines decision trees, deep convolutional networks, and probabilistic reasoning. [.pdf]

IA opportunities for precision agriculture

Career opportunity in Artificial Intelligence

Impact of artificial intelligence on the young graduate [.pdf]