Home

Selected Roles


2021
current

Postdoctoral Research Fellow,
Harvard University,
Boston, United States


2021
current

Postdoctoral Research Fellow,
Dana Farber,
Boston, United States


2021

AI Researcher,
Naver Labs,
Seoul, South Korea


2020
2021

Postdoctoral Research Associate,
University of Cambridge,
Cambridge, UK

Education

2017
2020

PhD in AI and Robotics,
University of Cambridge,
Cambridge, UK

2013
2017

BEng in AI and Software Engineering,
University of Edinburgh,
Edinburgh, UK

Biography

Luca Scimeca is a Machine Learning expert, with focus on Deep Learning, Probabilistic Machine Learning, Computer Vision, Biotechnology, Machine Learning for Healthcare and Robotics. Luca is currently an AI Research Fellow at both Harvard Medical School and Dana Farber, where he focuses on the use of Machine Learning for Medical applications. Prior to this, Luca was an AI researcher at NAVER Labs, South Korea, as well as a Post-Doctoral Research Associate at the University of Cambridge, where he conducted research at the university’s Biologically Inspired Robotics Laboratory (BIRL).

Luca received his First Class Bachelor of Engineering in Artificial Intelligence and Software Engineering from the University of Edinburgh, where he graduated summa cum laude, obtaining the Class award and Howe Prize for the best performance in Artificial Intelligence. During his studies Luca has won over 13 awards, 9 of which paid scholarships for academic performance.

In 2020 Luca Scimeca received his PhD in Engineering (Artificial Intelligence and Robotics) from the University of Cambridge. During the course of his PhD studies Luca has taken part to several research projects and competitions which led to over 14 high profile conference and journal publications.

Research

" I am interested in the intersection between AI and Medicine, and the use of Machine Learning to boost medical research and medical treatments. With a background in Machine Learning, Vision and Robotics, I am currently carrying out research on the use of deep learning and probabilistic machine learning to boost both the efficacy and applicability of cancer treatments, with particular focus on cancer immunotherapy and synthetic biology."

 

For a list of publications visit this link.

Highlights

RoboAnt

RoboAnt (University of Edinburgh, 2016-2017) As part of my thesis at the university …

Image Classification With CNNs (University of Edinburgh, 2016-2017) Tensor Flow Deep Neural Networks …

Hand-written Digit Classification with DNNs (University of Edinburgh, 2016) The code shows DNN …

MATLAB Object Recognition and Tracking (University of Edinburgh, 2016) The project was developed …