I hold a strong academic background in numerical fields, with a full-mark Master's degree in Mechatronics Engineering and a solid foundation in statistics.
My passion for Data and Optimization Algorithms led me to perform research activities and publish peer-reviewed articles in a high-impact journal about genetic algorithms for solving Multi-Objective Optimization problems.
In my professional career, I have worked as a production Data Analyst and currently hold a position as a Data Scientist, both in multinational companies.
I have spent the past years immersing myself in Machine Learning model development and database management.
One of my notable strengths lies in my communication skills. I am a regular contributor to Towards Data Science, a top data science blog, where I communicate technical concepts effectively to diverse audiences.
From the beginning of my academic and working career, I proved to be capable of easily learning new software and concepts, then implementing them.
This website, which I built by myself (starting from a template) is a demonstration of that.
This paper it is developed and presented a multi-objective optimization algorithm capable of solving PMU placement in power grids, while minimizing measurement uncertainty and economic costs....
This paper presents a tri-objective Optimal Phasor Measurement Units (PMUs) Placement (OPP) strategy that is focused on the minimization of i) the total number of PMU channels, ii) the maximum state estimation uncertainty ...
Remember that feeling after watching movies like EuroTrip, where the characters whisk through picturesque European cities on an adventure of a lifetime? It’s captivating....
To truly grasp the intricacies of Language Models (LM) and become familiar with their underlying principles, there is no other way than rolling up our sleeves and starting to write code...
Retrieving data from SpaceX API to develop a Machine Learning model able to predict if the Falcon 9 first stage will land successfully.
In this project, I build a deep neural network without the aid of any deep learning library (Tensorflow, Keras, Pytorch).
DEEP NETWORKS ● NETWORK ARCHITECTURE ● OPTIMIZATION ● HYPERPARAMETERS' TUNING ● CONVOLUTIONAL NEURAL NETWORKS
COMPUTER VISION ● TENSORFLOW ● NATURAL LANGUAGE PROCESSING ● TIME SERIES ● RNNs ● CNNs
MACHINE LEARNING ● PYTHON PROGRAMMING ● TEXT MINING ● DATA VISUALIZATION ● DATA CLEANING
MACHINE LEARNING ● OPTIMIZATION ● DATA SCIENCE METHODOLOGY
Published on: IEEE
This paper presents a tri-objective Optimal Phasor Measurement Units (PMUs) Placement (OPP) strategy that is focused on the minimization of i) the total number of PMU channels, ii) the maximum state estimation uncertainty ...
Published on: Towards Data Science
In the novel Flatland, characters living in a two-dimensional world find themselves perplexed and unable to comprehend when they encounter a three-dimensional being. I use this analogy ...
Published on: Towards Data Science
Imagine a room filled with colorful balloons, each symbolizing a data point in a dataset. Due to their different features, the balloons float at different heights. Now, picture some helium ...
Published on: Towards Data Science
In the refined atmosphere of 18th-century London, a pioneering individuals embarked on a quest that would forever alter our understanding of data and statistics. John Arbuthnot, a distinguished Scottish physician ...
Published on: Towards Data Science
How do streaming platforms like Netflix recommend the perfect movie for your evening? How can we optimize player positioning in sports like soccer? How can we identify fraudulent activities in financial networks? ...
Published on: Towards Data Science
SVM is a powerful and versatile algorithm, which, at its core, can delineate optimal hyperplanes in a high-dimensional space, effectively segregating the different classes of a dataset ...
Published on: Towards Data Science
Fundamental learning algorithms as logistic regression or linear regression are often too simple to achieve adequate results for a machine learning problem. While a possible solution is to use neural ...
Published on: Towards Data Science
As Computer Vision applications are becoming omnipresent in our lives, understanding the functioning principles of Convolutional Neural Networks is essential for every Data Science practitioner ...
Published on: Towards Data Science
As the nature of neural networks’ developing process is iterative, we need to take advantage of each possible expedient to minimize the training time ...
Published on: Towards Data Science
Training a neural network from scratch takes a great extent of time and huge computation power. One way to overcome both these obstacles is to implement transfer learning ...
Published on: Towards Data Science
Modern Deep Learning libraries are powerful tools but they may lead practitioners to take for granted neural networks’ functioning principles. In this project, I build a deep neural network without the aid of any deep learning library ...
Published on: Towards Data Science
When training a deep neural network, it’s often troublesome to achieve the same performances on both the training and validation sets. A considerably higher error on the validation set is a clear flag for ...
Published on: Towards Data Science
Optical Character Recognition (OCR) is present in our daily life more regularly than we imagine. When we use Google Translate to translate text from pic ...
Published on: Towards Data Science
Coding and explaining the process of synthetic data generation to enhance the accuracy of an OCR learning algorithm. One of the most reliable ways to enhance the performance of a low bias ...
Please, feel free to use this form to send me an email. I will answer ASAP.