368 citations · 862 across the 13 of their papers we have counts for
3 papers · 1 filter
Experience Replay for Continual Learning
David Rolnick, Arun Ahuja, Jonathan Schwarz +2
Continual learning is the problem of learning new tasks or knowledge while protecting old knowledge and ideally generalizing from old experience to learn new tasks faster. Neural n…
Neural Processes
Marta Garnelo, Jonathan Schwarz, Dan Rosenbaum +4
A neural network (NN) is a parameterised function that can be tuned via gradient descent to approximate a labelled collection of data with high precision. A Gaussian process (GP),…
Progress & Compress: A scalable framework for continual learning
Jonathan Schwarz, Jelena Luketina, Wojciech M. Czarnecki +4
We introduce a conceptually simple and scalable framework for continual learning domains where tasks are learned sequentially. Our method is constant in the number of parameters an…