Search Results for author: Luca Citi

Found 4 papers, 1 papers with code

Deep Learning in Target Space

1 code implementation2 Jun 2020 Michael Fairbank, Spyridon Samothrakis, Luca Citi

Experimental results show the speed of using target space, and examples of improved generalisation, for fully-connected networks and convolutional networks, and the ability to recall and process long time sequences and perform natural-language processing with recurrent networks.

Domain Adaptation for Deep Reinforcement Learning in Visually Distinct Games

no code implementations ICLR 2018 Dino S. Ratcliffe, Luca Citi, Sam Devlin, Udo Kruschwitz

Many deep reinforcement learning approaches use graphical state representations, this means visually distinct games that share the same underlying structure cannot effectively share knowledge.

Domain Adaptation Multi-Task Learning

A simple yet efficient algorithm for multiple kernel learning under elastic-net constraints

no code implementations29 Jun 2015 Luca Citi

This papers introduces an algorithm for the solution of multiple kernel learning (MKL) problems with elastic-net constraints on the kernel weights.

A Real-Time Automated Point-Process Method for the Detection and Correction of Erroneous and Ectopic Heartbeats

no code implementations2 Aug 2012 Luca Citi, Emery N. Brown, Riccardo Barbieri

Our automated algorithm represents an improvement over previous procedures, with best specificity for the detection of correct beats, as well as highest sensitivity to missed and extra beats, artificially misplaced beats, and for real arrhythmic events.

Heartbeat Classification Heart Rate Variability

Cannot find the paper you are looking for? You can Submit a new open access paper.