Exploring the intersections of machine learning, artificial intelligence, and complex systems.
I am a dedicated physicist with a BSc in Physics and an MSc in Physics of Data, with a strong passion for Data Science and Artificial Intelligence. My academic journey has centered on leveraging analytical and computational techniques to address complex systems and real-world challenges using cutting-edge technologies. Previously, I worked as a Quantitative Analyst at XSOR Capital, a London-based investment boutique, where I developed machine learning models for trading and implemented automated trading strategies. This experience honed my skills in applying data-driven approaches to solve high-impact financial problems. Currently, my research focuses on Spiking Neural Networks, exploring advanced architectures like Liquid State Machines and deep SNNs trained via reward-modulated STDP. I aim to push the boundaries of biologically inspired computing and its applications in intelligent systems.
The study of matter, energy, and the interactions between them. Physics explores concepts such as force, motion, and the fundamental nature of the universe. It is a cornerstone of scientific knowledge, providing insights into everything from subatomic particles to the vastness of space and time.
Deep learning is a branch of artificial intelligence that focuses on building and training neural networks to simulate human learning processes. By leveraging vast amounts of data and computational power, deep learning models are used to solve complex tasks like image recognition, natural language processing, and predictive analytics, enabling groundbreaking advancements in technology and science.
Artificial intelligence aims to create systems capable of performing tasks that typically require human intelligence. This includes problem-solving, decision-making, language understanding, and learning. AI drives innovations in numerous fields, transforming industries and enhancing human-computer interaction through smarter, more adaptive technologies.
Algorithmic trading combines finance and technology to develop automated systems that execute trades based on predefined strategies. These systems analyze financial markets, identify opportunities, and optimize portfolio performance. By integrating advanced algorithms and machine learning, algorithmic trading enhances efficiency, speed, and precision in financial decision-making.
Robotics involves the design, construction, and programming of intelligent machines capable of performing tasks in various environments. It merges engineering, computer science, and artificial intelligence to develop systems that assist humans in areas such as manufacturing, healthcare, and exploration, pushing the boundaries of automation and innovation.
Data science is the process of extracting meaningful insights from structured and unstructured data through statistical analysis, machine learning, and visualization techniques. It drives decision-making and innovation across industries by uncovering patterns, trends, and relationships within complex datasets.
Worked under the supervision of Prof. Michele Rossi on research involving Spiking
Neural Networks.
Key contributions included:
Contributed to the development of Machine Learning strategies for algorithmic
trading, focusing on financial time series prediction.
Key achievements included:
Gained hands-on experience in quantitative analysis and algorithmic trading.
Key responsibilities included:
🎯 Focused on Complex Systems, Data Science, and Deep Learning.
🖼️ Explored 2D and 3D Computer Vision and Big Data Management.
🧠 Advanced knowledge in Information Theory.
Vote: 110 cum laude / 110
🎯 Specialized in Computational Physics.
⚛️ Topics included Quantum Theory of Matter and Subnuclear Physics.
📈 Advanced Calculus and Statistics for Modelling and Data Analysis.
Vote: 106 / 110
Specialized in Applied Sciences, developing a strong foundation in Physics, Mathematics, and Computer Science.
Vote: 100 / 100
Outside of my academic and professional pursuits, I am an avid chess enthusiast who enjoys strategizing and problem-solving on the board. Chess has taught me patience, critical thinking, and the importance of planning ahead. I also have a deep appreciation for cinema and literature, with a particular interest in thought-provoking films and books spanning a variety of genres. You can find some of my movie reviews in the blog section of this site.
In my free time, I enjoy exploring topics in statistics and data analysis, often diving into side projects to deepen my understanding of complex systems. Additionally, I find joy in continuously learning about advancements in artificial intelligence and its intersection with human cognition.
Developed a machine learning model to detect radio wave activity from raw data, focusing on signal processing and communication systems. Utilized Python, scikit-learn, and custom data visualization to identify patterns in radio signals.
Designed and implemented spiking neural network architectures for temporal pattern recognition, leveraging reward-modulated STDP. Explored advanced training techniques using snnTorch and SpykeTorch, with experiments on Liquid State Machines and recurrent convolutional layers.
Created a quantitative trading strategy centered on volatility carry. Performed backtesting and optimization of trading models using Python libraries such as pandas, NumPy, and matplotlib to analyze market data and evaluate performance metrics.
Developed a system for real-time voice command recognition. Integrated signal processing techniques and machine learning models using tools like Librosa and PyTorch to detect specific keywords in audio streams with high accuracy.
Created a repository of mathematical models and algorithms for finance, including pricing derivatives, portfolio optimization, and risk analysis. Focused on clarity and precision, with implementations in Python.
Built a real-time data pipeline and dashboard to monitor cosmic ray activity using Apache Spark and Kafka. Processed high-frequency data streams and visualized results dynamically, showcasing expertise in distributed systems and real-time analytics.
Exploring Spiking Neural Networks for temporal pattern recognition, using biologically inspired architectures and advanced training techniques.
Investigated the Information Bottleneck method for analyzing trade-offs between representation compression and prediction accuracy in machine learning models.
Developed simulations and models for vehicular networks using game theory to optimize communication and resource allocation strategies.
Implemented CSRNet in PyTorch for crowd counting tasks, focusing on high-density population datasets and improving model accuracy and scalability.
If you’d like to connect, discuss collaborations, or have questions about my projects and research, feel free to reach out. I’m always open to interesting opportunities and conversations in the field of data science, artificial intelligence, and computational physics.
If you'd like to get in touch, feel free to use my contact form.