Posts
Unlocking the Power of Diffusion Models: A Dive into Relative Trajectory Balance
Unlocking the Power of Diffusion Models: A Dive into Relative Trajectory Balance In the ever-evolving landscape of artificial intelligence, diffusion models have emerged as a powerful tool for generating high-quality data across various domains such as images, text, and even action spaces. But what happens when we need these models to not just generate, but…
Shortcut Learning in Deep Neural Networks. Which cues will your model choose to learn? (ICLR 2022)
Shortcut Learning in Deep Neural Networks. Which cues will your model choose to learn? (ICLR 2022) Deep neural networks (DNNs) often rely on easily learned discriminatory features, or cues, that are not essential to the problem at hand, a phenomenon known as shortcut learning. For instance, DNNs may recognize ducks based on the typical background…
Da Palermo ad Harvard e la ricerca sul cancro: la storia di Luca Scimeca
An amazing article by Joey Borruso, telling the story of my journey, starting in Sicily, Italy… Full article at: https://palermolive.it/ricerca-cancro-luca-scimeca/
Introducing RoboPatient – a soft robotics approach to training doctors
An article published today by the University of Cambridge describes part of my work in using AI and Robotics in the medical field . Cambridge researchers are helping to design healthcare robotics of the future by investigating a robot-assisted approach to training doctors in medical examinations. To read the full article follow this link. We…
Gaussian process inference modelling of dynamic robot control for expressive piano playing
A robot that can autonomously learn to play piano by mimicking the dynamics of different human playing styles. Our most recent publication, in collaboration with Cheryn Ng, in the international journal PlosONE titled “Gaussian Process inference modelling of dynamic robot control for expressive piano playing”. In the paper we propose a Gaussian Process-based mathematical framework for…
Structuring of tactile sensory information for category formation in robotics palpation
Robotics and Medicine: one of our most recent publications in the journal “Autonomous Robots”, exploiting the application of machine learning and tactile sensing to aid in the autonomous detection of abnormal lumps in soft bodies. In collaboration with Perla Maiolino and Fumiya Iida. Full paper: https://lnkd.in/dcaaW2cVideos: https://lnkd.in/duz-jfZ
Something went wrong. Please refresh the page and/or try again.