Don't try to Escape it.
Enter it.

Take the red pill. Take the blue pill.

Eduardo Pigantelli
London, UK

Currently a Phd Candidate at UCL under the supervision of Laura Toni and Tim Rocktäschel

Hello there, I am Eduardo,
researcher in AI.

I started my professional journey five years ago between industry and academia. Thenceforth, I researched. My activity progressively shifted from design towards computer science, reinforcing my passion and interest in Artificial General Intelligence. In 2020 I joined the LASP group at UCL as a PhD student to consolidate the transition to AI and conduct research on Continual Learning and Reinforcement Learning. In 2019 I joined the BICI group at the Imperial College as a postdoc to study the applications of deep learning to solve differential equations in physics. At Burohappold Engineeering, in 2017, I specialised in machine learning, and lead the applied research group in Machine Learning and Decision Making in 2018. In 2014, at, I conducted research on generative design and multi-objective optimisation using genetic algorithms. I hold a bachelor and a in Architecture at the University of Naples, awarded in 2015, where I studied the role of human perception and the process of creative creation in design. Today, my research interests are in artificial general intelligence and autonomous learning, and include deep learning, reinforcement learning, multiagent systems, game theory and computer vision.


In 2020 I joined the Learning and Signal Processing (LASP) group at UCL as a PhD student. Under the supervision of Laura Toni and Tim Rocktäschel, my focus is on Continual Learning within the Multiagent Reinforcement Learning paradigm.

In 2019 I joined the Biologically-Inspired Computation and Inference Lab (BICI) at the Imperial College with a postdoc position funded by the Rosetrees Trust. Under the supervision of Anil Anthony Bharath and Chris Cantwell, I conducted research to shorten the computational time for predictive modelling of surgical interventions in cardiology. I used deep learning to infer approximate solutions in about 1% of time necessary to canonical methods The project is a multidisciplinary initiative that brings together the National Heart and Lung Institute, and the Departments of Bioengineering, Aeronautics, Computing and Physics to address key challenges in the diagnosis and treatment of complex cardiac arrhythmias.

In 2017 I joined BuroHappold Engineering, where I improved my skills in software architecture, supporting on the framework architecture and designing the user interface of the BHoM. I specialised in Machine Learning, and in 2018 I led the applied research in Machine Learning and Decision Making. I worked to democratise the access to Deep Learning technologies to allow every employee to access the knowledge and the tools. I used Visual Programming, a recognised and diffused tool for design, to create a framework that interoperates between the most common deep learning libraries, tensorflow, keras, pytorch, numpy.

In 2015 I defended the thesis “Computational morphogenesis and construction of an acoustic shell for outdoor chamber music”. Implementing numerical methods that uses geometrical acoustics, computational physics, descriptive geometry and genetic algorithms, the work established the state of the art for generative method of passive acoustic shell for outdoor classical music.

In 2014 I joined, earlier as Intern and later as a Computational Design Specialist. is an research firm that specialises in computational design. We studied how multi-objective optimisation and evolutionary algorithms can be employed to transform traditional, ancient building techniques into cost-effective and culture-preserving options.