Hi there! I’m Emanuele, a final-year BSc student in Physics and volunteer research assistant in Artificial Intelligence and Cyber-Physical Systems with the Bortolussi Group (a.k.a. [email protected]) at the University of Trieste (Italy).
During my studies I focused mainly on statistical/computational methods for data analysis in experimental physics and signal processing. More recently, I moved toward more general artificial intelligence, (statistical) machine learning and analysis of massive datasets, mainly centered around decision problems and planning/control, both theoretical and applied.
My main research interests include:
- Core methods in classical statistics and machine learning (i.e. decision trees, boosting, Petri nets, genetic programming);
- Core methods for optimization in highly-dimensional manifolds with minimal assumptions (i.e. SGD, MonteCarlo-based, tempering);
- Artificial neural computation and deep learning (i.e. CNNs, RNNs, autoencoders/VAEs, GANs, novel neural architectures, neural ODEs);
- Statistical network models for inference (i.e. energy-based NN, Boltzmann machines, Belief Networks) or simulation (i.e. diffusive processes on networks, computational epidemiology);
- Bayesian statistics and Bayesian ML methods - shallow and deep - including approximate variational inference;
- Prediction and control - through reinforcement (including Deep RL), logic and hybrid approaches - under uncertainty and/or in complex environments;
- Scientific high-performance computing, and, more generally, ways to harness computational power and efficiency from dedicated hardware architectures (i.e. GPGPU computing, neuro-/physio-morphic hardware).
I am deeply fascinated, too, by the bidirectional interplay between artificial and biological intelligence (i.e. bio-inspired AI methods, unconventional computing; AI applied to systems biology and neuroscience), and between artificial intelligence and physics (i.e. quantum machine learning; machine learning in high-energy physics).
When not about any of the above, I usually rant about optimality in policy-making and politics, energy policy, and open science/software.
Also, I usually don’t bite.
My (computational) toolbox
In trying to solve whichever problem I have at hand, I will happily use any combination of the following, provided they run on Linux.
- Python & its ecosystem (NumPy, SciPy, Pandas, PyTorch, Keras, modern TensorFlow, …);
- Modern C++ (>=2011) with libraries (ROOT, Armadillo, Boost, …);
- Integrated computational languages/environments, i.e. MATLAB and Wolfram Mathematica;
- Bash/Zsh as a scripting language for basic orchestration and system automation;
- Fortran, F# or R if no other option exist or I feel brave enough.
I’m also a diehard user of mechanical pencils and liquid-ink-based pens, for the purposes of problem solving - computational or otherwise.