🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Interpretable AI for policy-making in pandemics deepai.org/publication/in… by Leonardo Lucio Custode and Giovanni Iacca #EvolutionaryComputation #ReinforcementLearning

I'm looking for candidates for 5 PhD positions and one postdoc, on various topics related to (distributed) machine learning, numerical optimization, evolutionary robotics and quantum computing. Contact me if interested. #phdposition #postdocposition #acad…lnkd.in/e49D2h4b

This paper presents a method using #MachineLearning for automatic COVID-19 patient-stratification based on standardised lung #ultrasound data: doi.org/10.1121/2.0001… Leonardo Lucio Custode Giovanni Iacca @ULTRaTrento #acoustics

Interested in Interpretable or Explainable Reinforcement Learning? In our latest published article, Giovanni Iacca and I present a method to perform Reinforcement Learning with Decision Trees, matching the state of the art in several benchmarks. Check it out: ieeexplore.ieee.org/document/10015…

I'm super-proud of Leonardo Lucio Custode! He is the first PhD graduate (cum laude!) in my group at Università di Trento UniTrento_DISI . Thanks Doina Jaume Bacardit and Libertario Demi (@ULTRaTrento) for your participation to the defense and for the wonderful discussion. Ad maiora!

Also this year, my lab is one of the possible hosts for the SPECIES scholarships for visiting PhD students. More info at: species-society.org/scholarships-2… #MachineLearning #visiting #phd #research #artificalintelligence #evolutionarycomputation

Have you ever wondered what's so special about the graph structure of Sparse Neural Networks? We present a new graph encoding to study the topological features of SNNs and how they correlate with performance. arxiv.org/abs/2305.16886 #deeplearning Elia Cunegatti Doina

New paper out! sciencedirect.com/science/articl… We propose an evolutionary computation method for interpretable multi-agent reinforcement learning tasks. Leonardo Lucio Custode Andrea Ferigo and Marco Crespi. #XAI #MachineLearning

I am happy to share our recent paper on quality-diversity #optimization of #decisiontrees for #reinforcementlearning tasks. This approach can be useful to achieve #interpretability and #explainableai. #MachineLearning #xAI Andrea Ferigo Leonardo Lucio Custode doi.org/10.1007/s00521…

Our GECCO 2025 papers are finally out! Multi-Objective Evolutionary Hindsight Experience Replay for Robotics doi.org/10.1145/363852… Decentralized Federated NeuroEvolution of Heterogeneous Networks doi.org/10.1145/363852… Neuron-centric Hebbian Learning doi.org/10.1145/363852…

Happy to share that we won the Interpretable Control Competition @ #GECCO24 ! Congrats Mátyás Vincze Laura Ferrarotti Giovanni Iacca Bruno Lepri

New paper out! Fast-Inf: Ultra-Fast Embedded Intelligence on the Batteryless Edge dl.acm.org/doi/10.1145/36… #tinyml #machinelearning #artificialintelligence

🎉 Our work "SMOSE: Sparse Mixture of Shallow Experts for Interpretable Reinforcement Learning in Continuous Control Tasks" has been accepted by AAAI 2025! #AAAI2025 paper: arxiv.org/abs/2412.13053 with Laura Ferrarotti, Bruno Lepri, Giovanni Iacca 🧵1/6