Search Results for author: Michele Franceschini

Found 2 papers, 0 papers with code

Generation and Consolidation of Recollections for Efficient Deep Lifelong Learning

no code implementations ICLR 2018 Matt Riemer, Michele Franceschini, and Tim Klinger

In this paper, we explore the relationship between lossy compression and the resource constrained lifelong learning problem of function transferability.

Knowledge Distillation

Scalable Recollections for Continual Lifelong Learning

no code implementations17 Nov 2017 Matthew Riemer, Tim Klinger, Djallel Bouneffouf, Michele Franceschini

Given the recent success of Deep Learning applied to a variety of single tasks, it is natural to consider more human-realistic settings.

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